sowson / darknet Goto Github PK

Darknet on OpenCL Convolutional Neural Networks on OpenCL on Intel & NVidia & AMD & Mali GPUs for macOS & GNU/Linux & Windows & FreeBSD

Home Page: http://pjreddie.com/darknet/

License: Other

Makefile 0.38% Python 0.70% C 96.23% Shell 0.15% C++ 1.00% CMake 1.52%

darknet opencl c amd intel nvidia cpu gpu freebsd linux

darknet's Introduction

THE LAST COMMIT, ALL THE BEST FOR YOU!

Project Status: Freeze!

From now on, I will not push anymore my commits to this repository, however, I will be open to your pull requests to approve those and increase the contributors' list, Enjoy! ;-). I think OpenCL has a bright future, I am leaving some open issues, and I hope community will be able to solve them if needed. Thank you! ;-).

Build on macOS or Ubuntu 20.04

Step by step in command prompt guide: https://iblog.isowa.io/2018/05/26/darknet-training

Build on Windows 10 or 11 x64

Step by step experimental guide: https://iblog.isowa.io/2021/11/20/darknet-on-opencl-on-windows-11-x64

Take a look 4 x GPUs on macOS (click to see video)

CLBlast instead of clBLAS for GEMM

git apply patches/clblast.patch

Darknet-vNext (Improved CUDA DarkNet)

DarkNet-vNext Link If you are looking for engine that has all the same functions, but it is FASTER!

OpenCV 4

This engine runs on OpenCV v4! But, OpenCV v3 is also fine!

YOLO4 on OpenCL

YOLO4 elements are supported, remember in CFG file to use [yolo4] instead of [yolo] to make it work!

YOLO1, YOLO2, YOLO3 on OpenCL

https://iblog.isowa.io/2020/07/02/the-multi-gpu-set-idea

https://iblog.isowa.io/2020/06/22/gpu-opencl-fine-tuning-problem-solution

https://iblog.isowa.io/2020/05/31/ph-d-hanna-hackintosh-is-ready

https://iblog.isowa.io/2020/04/29/darknet-in-opencl-on-beagleboard-ai

https://iblog.isowa.io/2020/03/03/is-opencl-beats-cuda

https://iblog.isowa.io/2020/03/02/hania-pc-well-it-needs-macos

https://iblog.isowa.io/2020/02/08/pc-for-phd-studies

https://iblog.isowa.io/2020/01/04/gpu-opencl-fine-tuning-problem

https://iblog.isowa.io/2019/12/29/darknet-cuda-vs-opencl-and-cpu-vs-nvidia-vs-amd

https://iblog.isowa.io/2019/11/05/gpu-computing-on-opencl

https://iblog.isowa.io/2019/08/18/the-fastest-darknet-in-opencl-on-the-planet

https://iblog.isowa.io/2019/02/02/darknet-in-opencl-on-asus-thinker-board-s

https://iblog.isowa.io/2018/08/01/darknet-in-opencl

https://iblog.isowa.io/2018/05/26/darknet-training

Thanks!

darknet's People

Contributors

Stargazers

Watchers

darknet's Issues

segfault

This is a bit esoteric question, but ..

I linked your branch of darknet against this one:

https://github.com/CNugteren/CLBlast

It compiles ok, but when running the darknet executable, I get a segfault.

System: Ubuntu 18.04 LTS with intel

Any comments? Am I doing something that I shouldn't..?

Changing the name of the .txt file

Hello @sowson, when I was trying to train a yolov3-tiny model, I ran into an error. The program couldn't open the file labels_19886_r270.txt. When I checked the file, I found that I don't have a file by that name, instead I have one by the name images_19886_r270.txt, the same as the name of the jpg file.

Since I am not familiar with the code of darknet, can you tell what I can change to fix this??

Here's the image of the output, just in case -

Thanks for the help

Issues Training on Macbook 2019

Hello, @sowson thanks for creating this project. It’s a great project!

I hit some issues and want to confirm how to train the YOLO v3 model on MacBook Pro 2019(With below Graphics: AMD Radeon Pro 5300M 4 GB and Intel UHD Graphics 630 1536 MB)

First I tried training without using AMD graphics, just in Makefile, change the GPU=1, without other changes. (It seems in this way, it’s using the Intel Graphics) .Then run “make”, and execute the training job below “./darknet detector train cfg/yolov3.data cfg/yolov3.cfg ./darknet53.conv.74”
The training dataset and parameters has been verified on Nvidia server with this repo(OpenCL for YOLOv3), it works well.

But on MacBook 2019, it hit the issue below:

From iteration 3, the loss became abnormal and then in following iteration, all value became “”NAN . I tried it multiple times, it either has issue in the 2nd iteration or the 3rd iteration.

Details logs as below. Would you advise? Thanks a lot.

Device IDs: 2
Device ID: 0
Device name: Intel(R) UHD Graphics 630
Device vendor: Intel Inc.
Device opencl availability: OpenCL 1.2
Device opencl used: 1.2(Jul 6 2020 11:56:19)
Device double precision: NO
Device max group size: 256
Device address bits: 64
my_data
layer filters size input output
0 conv 32 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 32 0.299 BFLOPs
1 conv 64 3 x 3 / 2 416 x 416 x 32 -> 208 x 208 x 64 1.595 BFLOPs
2 conv 32 1 x 1 / 1 208 x 208 x 64 -> 208 x 208 x 32 0.177 BFLOPs
3 conv 64 3 x 3 / 1 208 x 208 x 32 -> 208 x 208 x 64 1.595 BFLOPs
4 res 1 208 x 208 x 64 -> 208 x 208 x 64
5 conv 128 3 x 3 / 2 208 x 208 x 64 -> 104 x 104 x 128 1.595 BFLOPs
6 conv 64 1 x 1 / 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BFLOPs
7 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
8 res 5 104 x 104 x 128 -> 104 x 104 x 128
9 conv 64 1 x 1 / 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BFLOPs
10 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
11 res 8 104 x 104 x 128 -> 104 x 104 x 128
12 conv 256 3 x 3 / 2 104 x 104 x 128 -> 52 x 52 x 256 1.595 BFLOPs
13 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
14 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
15 res 12 52 x 52 x 256 -> 52 x 52 x 256
16 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
17 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
18 res 15 52 x 52 x 256 -> 52 x 52 x 256
19 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
20 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
21 res 18 52 x 52 x 256 -> 52 x 52 x 256
22 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
23 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
24 res 21 52 x 52 x 256 -> 52 x 52 x 256
25 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
26 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
27 res 24 52 x 52 x 256 -> 52 x 52 x 256
28 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
29 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
30 res 27 52 x 52 x 256 -> 52 x 52 x 256
31 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
32 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
33 res 30 52 x 52 x 256 -> 52 x 52 x 256
34 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
35 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
36 res 33 52 x 52 x 256 -> 52 x 52 x 256
37 conv 512 3 x 3 / 2 52 x 52 x 256 -> 26 x 26 x 512 1.595 BFLOPs
38 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
39 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
40 res 37 26 x 26 x 512 -> 26 x 26 x 512
41 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
42 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
43 res 40 26 x 26 x 512 -> 26 x 26 x 512
44 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
45 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
46 res 43 26 x 26 x 512 -> 26 x 26 x 512
47 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
48 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
49 res 46 26 x 26 x 512 -> 26 x 26 x 512
50 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
51 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
52 res 49 26 x 26 x 512 -> 26 x 26 x 512
53 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
54 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
55 res 52 26 x 26 x 512 -> 26 x 26 x 512
56 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
57 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
58 res 55 26 x 26 x 512 -> 26 x 26 x 512
59 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
60 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
61 res 58 26 x 26 x 512 -> 26 x 26 x 512
62 conv 1024 3 x 3 / 2 26 x 26 x 512 -> 13 x 13 x1024 1.595 BFLOPs
63 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
64 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
65 res 62 13 x 13 x1024 -> 13 x 13 x1024
66 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
67 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
68 res 65 13 x 13 x1024 -> 13 x 13 x1024
69 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
70 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
71 res 68 13 x 13 x1024 -> 13 x 13 x1024
72 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
73 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
74 res 71 13 x 13 x1024 -> 13 x 13 x1024
75 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
76 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
77 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
78 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
79 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
80 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
81 conv 27 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 27 0.009 BFLOPs
82 yolo
83 route 79
84 conv 256 1 x 1 / 1 13 x 13 x 512 -> 13 x 13 x 256 0.044 BFLOPs
85 upsample 2x 13 x 13 x 256 -> 26 x 26 x 256
86 route 85 61
87 conv 256 1 x 1 / 1 26 x 26 x 768 -> 26 x 26 x 256 0.266 BFLOPs
88 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
89 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
90 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
91 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
92 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
93 conv 27 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 27 0.019 BFLOPs
94 yolo
95 route 91
96 conv 128 1 x 1 / 1 26 x 26 x 256 -> 26 x 26 x 128 0.044 BFLOPs
97 upsample 4x 26 x 26 x 128 -> 104 x 104 x 128
98 route 97 11
99 conv 128 1 x 1 / 1 104 x 104 x 256 -> 104 x 104 x 128 0.709 BFLOPs
100 conv 256 3 x 3 / 1 104 x 104 x 128 -> 104 x 104 x 256 6.380 BFLOPs
101 conv 128 1 x 1 / 1 104 x 104 x 256 -> 104 x 104 x 128 0.709 BFLOPs
102 conv 256 3 x 3 / 1 104 x 104 x 128 -> 104 x 104 x 256 6.380 BFLOPs
103 conv 128 1 x 1 / 1 104 x 104 x 256 -> 104 x 104 x 128 0.709 BFLOPs
104 conv 256 3 x 3 / 1 104 x 104 x 128 -> 104 x 104 x 256 6.380 BFLOPs
105 conv 27 1 x 1 / 1 104 x 104 x 256 -> 104 x 104 x 27 0.150 BFLOPs
106 yolo
Loading weights from ./darknet53.conv.74...Done!
Learning Rate: 0.001, Momentum: 0.9, Decay: 0.0005
Saving weights to ./weights//training1.conv.weights
Resizing
576
Loaded: 0.000021 seconds
Region 82 Avg IOU: 0.669766, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.885020, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 1.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.354004, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.366495, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.456132, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.429546, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.598901, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.286972, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.369272, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.544681, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.448270, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.776807, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 1.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.521708, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.512312, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.417380, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.644111, Class: 0.500000, Obj: 0.500000, No Obj: 0.500000, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500000, .5R: nan, .75R: nan, count: 0
1: 5589.400879, 5589.400879 avg, 0.000000 rate, 120.103433 seconds, 16 images
Loaded: 0.000050 seconds
Region 82 Avg IOU: 0.348210, Class: 0.505208, Obj: 0.493800, No Obj: 0.491735, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.491735, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.425261, Class: 0.499420, Obj: 0.498816, No Obj: 0.500049, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.412689, Class: 0.505208, Obj: 0.493800, No Obj: 0.491735, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.339118, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.491735, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.442617, Class: 0.499420, Obj: 0.498816, No Obj: 0.500049, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.428194, Class: 0.490482, Obj: 0.493800, No Obj: 0.491735, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.491735, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.460231, Class: 0.499420, Obj: 0.498816, No Obj: 0.500049, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.631038, Class: 0.505208, Obj: 0.493800, No Obj: 0.491735, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.339118, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.381417, Class: 0.505208, Obj: 0.493800, No Obj: 0.491735, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.491735, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.500166, Class: 0.499420, Obj: 0.498816, No Obj: 0.500049, .5R: 1.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.339118, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.491735, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.625354, Class: 0.499420, Obj: 0.498816, No Obj: 0.500049, .5R: 1.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.645166, Class: 0.490482, Obj: 0.493800, No Obj: 0.491735, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.339118, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.246722, Class: 0.501013, Obj: 0.490056, No Obj: 0.491735, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.425910, Class: 0.471722, Obj: 0.492571, No Obj: 0.491735, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.371427, Class: 0.483262, Obj: 0.493800, No Obj: 0.491735, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.339118, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.491735, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.439371, Class: 0.499015, Obj: 0.501104, No Obj: 0.500049, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519303, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.513600, Class: 0.483262, Obj: 0.493800, No Obj: 0.491735, .5R: 1.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.500049, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.339118, .5R: nan, .75R: nan, count: 0
2: 6445.931641, 5675.054199 avg, 0.000000 rate, 120.592475 seconds, 32 images
Loaded: 0.000044 seconds
Region 82 Avg IOU: 0.000000, Class: 1.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519444, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 1.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.395062, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.481045, Class: 0.492256, Obj: 0.472559, No Obj: 0.477005, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: 1.000000, Obj: 0.500000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 2
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.395062, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.454574, Class: 0.451919, Obj: 0.437122, No Obj: 0.477005, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.395062, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.397417, Class: 0.492256, Obj: 0.472559, No Obj: 0.477005, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519444, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.395062, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.323605, Class: 0.451919, Obj: 0.437122, No Obj: 0.477005, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 1.000000, Obj: 1.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519444, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 1.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.395062, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: 0.352548, Class: 0.451919, Obj: 0.437122, No Obj: 0.477005, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 1.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519444, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 0.000000, Obj: 1.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.519444, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 1.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 0.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 0.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: 0.000000, Class: 0.000000, Obj: 0.000000, No Obj: 0.395062, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.477005, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: 0.662166, .5R: nan, .75R: nan, count: 0
3: 6776393516076498944.000000, 677639324119859200.000000 avg, 0.000000 rate, 120.494957 seconds, 48 images
Loaded: 0.000044 seconds
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
4: nan, nan avg, 0.000000 rate, 118.672016 seconds, 64 images
Loaded: 0.000047 seconds
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1
Region 94 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 106 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: nan, .75R: nan, count: 0
Region 82 Avg IOU: nan, Class: nan, Obj: nan, No Obj: nan, .5R: 0.000000, .75R: 0.000000, count: 1

CL_OUT_OF_RESOURCES error when training in classifier .

Hello, @sowson thank your great work.
I used this project for training yolov3 with opencl, and it worked very well. But when training a classifier, there is a opencl backward_scale_kernel error: CL_OUT_OF_RESOURCES. I want to know if there are some problem with my way.

I used a customize dataset with 2 classes, and modified filters of the last convolution layer in cfg/darknet19.cfg.

Here are my spec:
$ ./darknet classifier Device IDs: 2
Device ID: 0
Device name: Tesla V100-PCIE-16GB
Device vendor: NVIDIA Corporation
Device opencl availability: Device opencl used: 440.33.01
Device double precision: YES
Device max group size: 1024
Device address bits: 64
darknet19
1
layer filters size 0 conv 32 3 x 3 / 1 1 max 2 x 2 / 2 2 conv 64 3 x 3 / 1 3 max 2 x 2 / 2 4 conv 128 3 x 3 / 1 5 conv 64 1 x 1 / 1 6 conv 128 3 x 3 / 1 7 max 2 x 2 / 2 8 conv 256 3 x 3 / 1 9 conv 128 1 x 1 / 1 10 conv 256 3 x 3 / 1 11 max 2 x 2 / 2 12 conv 512 3 x 3 / 1 13 conv 256 1 x 1 / 1 14 conv 512 3 x 3 / 1 15 conv 256 1 x 1 / 1 16 conv 512 3 x 3 / 1 17 max 2 x 2 / 2 18 conv 1024 3 x 3 / 1 19 conv 512 1 x 1 / 1 20 conv 1024 3 x 3 / 1 21 conv 512 1 x 1 / 1 22 conv 1024 3 x 3 / 1 23 conv 2 1 x 1 / 1 24 avg 25 softmax Learning Rate: 0.1, 384
128 448
Saving weights to Loaded: 0.000083 seconds
opencl backward_scale_kernel train dogs/dogs.data cfg/darknet19.cfg
OpenCL 1.2 CUDA
input output
256 x 256 x 3 -> 256 x 256 x 32 0.113 BFLOPs
256 x 256 x 32 -> 128 x 128 x 32
128 x 128 x 32 -> 128 x 128 x 64 0.604 BFLOPs
128 x 128 x 64 -> 64 x 64 x 64
64 x 64 x 64 -> 64 x 64 x 128 0.604 BFLOPs
64 x 64 x 128 -> 64 x 64 x 64 0.067 BFLOPs
64 x 64 x 64 -> 64 x 64 x 128 0.604 BFLOPs
64 x 64 x 128 -> 32 x 32 x 128
32 x 32 x 128 -> 32 x 32 x 256 0.604 BFLOPs
32 x 32 x 256 -> 32 x 32 x 128 0.067 BFLOPs
32 x 32 x 128 -> 32 x 32 x 256 0.604 BFLOPs
32 x 32 x 256 -> 16 x 16 x 256
16 x 16 x 256 -> 16 x 16 x 512 0.604 BFLOPs
16 x 16 x 512 -> 16 x 16 x 256 0.067 BFLOPs
16 x 16 x 256 -> 16 x 16 x 512 0.604 BFLOPs
16 x 16 x 512 -> 16 x 16 x 256 0.067 BFLOPs
16 x 16 x 256 -> 16 x 16 x 512 0.604 BFLOPs
16 x 16 x 512 -> 8 x 8 x 512
8 x 8 x 512 -> 8 x 8 x1024 0.604 BFLOPs
8 x 8 x1024 -> 8 x 8 x 512 0.067 BFLOPs
8 x 8 x 512 -> 8 x 8 x1024 0.604 BFLOPs
8 x 8 x1024 -> 8 x 8 x 512 0.067 BFLOPs
8 x 8 x 512 -> 8 x 8 x1024 0.604 BFLOPs
8 x 8 x1024 -> 8 x 8 x 2 0.000 BFLOPs
8 x 8 x 2 -> 2
2
Momentum: 0.9, Decay: 0.0005
dogs/backup/darknet19.start.conv.weights
error: CL_OUT_OF_RESOURCES

I set breakpoint in opencl.c , and it finally positioned to line 837 with :
clErr = clEnqueueNDRangeKernel(opencl_queues[opencl_device_id_t], kernel, 2, globalOffser, globalItems, localItems, 0, NULL, NULL);
And it is in the backward_gpu function of a convolution layer.

Thanks a lot

CLBlast Support

If someone is interested :D. But keep in mind it not supports MultiGPU because CLBlast is also like clBLAS not Thread-Safe. Sorry :D.

clblast.path.txt

Thanks!

Yolov4-tiny not showing detections

The window of the picture is showing, the image is there, but I can not see any detections... I use the following command:

user@user-pc:~/darknet$ ./darknet detector test cfg/coco.data cfg/yolov4-tiny.cfg weights/yolov4-tiny.weights data/dog.jpg 
Device IDs: 1
Device ID: 0
Device name: Ellesmere
Device vendor: Advanced Micro Devices, Inc.
Device opencl availability: OpenCL 1.2 AMD-APP (3180.7)
Device opencl used: 3180.7
Device double precision: YES
Device max group size: 256
Device address bits: 64
layer     filters    size              input                output
    0 conv     32  3 x 3 / 2   416 x 416 x   3   ->   208 x 208 x  32  0.075 BFLOPs
    1 conv     64  3 x 3 / 2   208 x 208 x  32   ->   104 x 104 x  64  0.399 BFLOPs
    2 conv     64  3 x 3 / 1   104 x 104 x  64   ->   104 x 104 x  64  0.797 BFLOPs
    3 route  2
Unused field: 'groups = 2'
Unused field: 'group_id = 1'
    4 conv     32  3 x 3 / 1   104 x 104 x  64   ->   104 x 104 x  32  0.399 BFLOPs
    5 conv     32  3 x 3 / 1   104 x 104 x  32   ->   104 x 104 x  32  0.199 BFLOPs
    6 route  5 4
    7 conv     64  1 x 1 / 1   104 x 104 x  64   ->   104 x 104 x  64  0.089 BFLOPs
    8 route  2 7
    9 max          2 x 2 / 2   104 x 104 x 128   ->    52 x  52 x 128
   10 conv    128  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x 128  0.797 BFLOPs
   11 route  10
Unused field: 'groups = 2'
Unused field: 'group_id = 1'
   12 conv     64  3 x 3 / 1    52 x  52 x 128   ->    52 x  52 x  64  0.399 BFLOPs
   13 conv     64  3 x 3 / 1    52 x  52 x  64   ->    52 x  52 x  64  0.199 BFLOPs
   14 route  13 12
   15 conv    128  1 x 1 / 1    52 x  52 x 128   ->    52 x  52 x 128  0.089 BFLOPs
   16 route  10 15
   17 max          2 x 2 / 2    52 x  52 x 256   ->    26 x  26 x 256
   18 conv    256  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 256  0.797 BFLOPs
   19 route  18
Unused field: 'groups = 2'
Unused field: 'group_id = 1'
   20 conv    128  3 x 3 / 1    26 x  26 x 256   ->    26 x  26 x 128  0.399 BFLOPs
   21 conv    128  3 x 3 / 1    26 x  26 x 128   ->    26 x  26 x 128  0.199 BFLOPs
   22 route  21 20
   23 conv    256  1 x 1 / 1    26 x  26 x 256   ->    26 x  26 x 256  0.089 BFLOPs
   24 route  18 23
   25 max          2 x 2 / 2    26 x  26 x 512   ->    13 x  13 x 512
   26 conv    512  3 x 3 / 1    13 x  13 x 512   ->    13 x  13 x 512  0.797 BFLOPs
   27 conv    256  1 x 1 / 1    13 x  13 x 512   ->    13 x  13 x 256  0.044 BFLOPs
   28 conv    512  3 x 3 / 1    13 x  13 x 256   ->    13 x  13 x 512  0.399 BFLOPs
   29 conv    255  1 x 1 / 1    13 x  13 x 512   ->    13 x  13 x 255  0.044 BFLOPs
   30 yolo4
[yolo4] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
nms_kind: greedynms (1), beta = 0.600000 
   31 route  27
   32 conv    128  1 x 1 / 1    13 x  13 x 256   ->    13 x  13 x 128  0.011 BFLOPs
   33 upsample            2x    13 x  13 x 128   ->    26 x  26 x 128
   34 route  33 23
   35 conv    256  3 x 3 / 1    26 x  26 x 384   ->    26 x  26 x 256  1.196 BFLOPs
   36 conv    255  1 x 1 / 1    26 x  26 x 256   ->    26 x  26 x 255  0.088 BFLOPs
   37 yolo4
[yolo4] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
nms_kind: greedynms (1), beta = 0.600000 
Loading weights from weights/yolov4-tiny.weights...Done!
data/dog.jpg: Predicted in 0.393254 seconds.
user@user-pc:~/darknet$

Yolo3, yolo3-tiny and yolo4 are working as expected. Is this because yolo4-tiny is not supported?

Link to article missing

Thanks for doing work on this.

It'd be great if we had a short README here wrt. how to build/test your project.

Link to this: https://codingbytodesign.net/2018/05/26/darknet-training/ could be helpful, alternatively.

NVIDIA OpenCL OUT of RESOURCES Issue

Hi, maybe you know why on NVIDIA this engine faces OOR issue? Is there specific for NVIDIA OpenCL that it not release correctly GPU mem registers?

Any plan to make a Python Interface to use OpenCL?

I really Impressed your work done on OpenCL Darknet fork! I have tried your fork and able to use AMD Radeon Pro 560 on my macbook pro 2017! Do you have any plan to make a python interface to use the AMD GPU?

Could not train Yolo1, Yolo2, Yolo3 models, loss not going down

I already fix that issue in the latest commit and it should be fine now :D. Thanks!

OpenCV 4 support

Device ID: 0
Device name: gfx803
Device vendor: Advanced Micro Devices, Inc.
Device opencl availability: OpenCL 1.2 
Device opencl used: 2924.0 (HSA1.1,LC)
Device double precision: YES
Device max group size: 256
Device address bits: 64
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

That's all the output I get. I'm running on the official AMD ROCm OpenCL implementation on Arch Linux. The card is RX590. I tested OpenCL with hashcat and it worked there.

EDIT: Also, I was trying to run a simple detector: ./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights vid1.mp4

opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS

OS: Ubuntu 20.04.1 LTS

I have a RTX580, so I am using rocm and the opencl it comes with. I have successfully built darknet, but whenever I try to run it I get the following output:

user@user-pc:~/darknet-1.2$ ./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights
Device IDs: 1
Device ID: 0
Device name: gfx803
Device vendor: Advanced Micro Devices, Inc.
Device opencl availability: OpenCL 1.2 
Device opencl used: 3137.0 (HSA1.1,LC)
Device double precision: YES
Device max group size: 256
Device address bits: 64
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

user@user-pc:~/darknet-1.2$

What am I doing wrong?
Does opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS mean something is wrong with my opencl? or is it the way I built darknet?
My google-fu was useless.

undefined reference to 'avg_predictions'

When I was trying to make this project, it returned 1, and said that:
/usr/bin/ld: obj/yolo.o: in function test_yolo4': yolo.c:(.text+0x334a): undefined reference to avg_predictions'
collect2: error: ld returned 1 exit status
make: *** [Makefile:137：darknet] 错误 1

Seems like an easy problem, maybe inputting some words to 'makefile' can work, but I don't know how to fix it...

OpenCL issues on AMD RX580

Hi @sowson
I am really impressed about your OpenCL darknet fork. I have tried several OpenCL implementations including implementations from OpenCV (Master) and the Halide project. Most solutions were slow or had other hardware issues.

I tested your version of darknet with a NVIDIA 1070 and a AMD RX580. It works well on the NVIDIA GPU, but fails with several errors on the AMD.

Device ID: 0
Device name: Ellesmere
Device vendor: Advanced Micro Devices, Inc.
Device opencl availability: OpenCL 1.2 AMD-APP (2671.3)
Device opencl used: 2671.3
Device double precision: YES
Device max group size: 256
Device address bits: 64
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel activate_array_kernel.
opencl_create_kernel: Could not create kernel gradient_array_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel test_kernel.
opencl_create_kernel: Could not create kernel softmax_device.
opencl_create_kernel: Could not create kernel scale_bias_kernel.
opencl_create_kernel: Could not create kernel backward_scale_kernel.
opencl_create_kernel: Could not create kernel add_bias_kernel.
opencl_create_kernel: Could not create kernel backward_bias_kernel.
opencl_create_kernel: Could not create kernel adam_kernel.
opencl_create_kernel: Could not create kernel normalize_kernel.
opencl_create_kernel: Could not create kernel normalize_delta_kernel.
opencl_create_kernel: Could not create kernel l2norm_kernel.
opencl_create_kernel: Could not create kernel variance_delta_kernel.
opencl_create_kernel: Could not create kernel accumulate_kernel.
opencl_create_kernel: Could not create kernel mean_delta_kernel.
opencl_create_kernel: Could not create kernel mean_kernel.
opencl_create_kernel: Could not create kernel variance_kernel.
opencl_create_kernel: Could not create kernel reorg_kernel.
opencl_create_kernel: Could not create kernel axpy_kernel.
opencl_create_kernel: Could not create kernel pow_kernel.
opencl_create_kernel: Could not create kernel const_kernel.
opencl_create_kernel: Could not create kernel constrain_kernel.
opencl_create_kernel: Could not create kernel supp_kernel.
opencl_create_kernel: Could not create kernel add_kernel.
opencl_create_kernel: Could not create kernel scal_kernel.
opencl_create_kernel: Could not create kernel fill_kernel.
opencl_create_kernel: Could not create kernel mask_kernel.
opencl_create_kernel: Could not create kernel copy_kernel.
opencl_create_kernel: Could not create kernel mul_kernel.
opencl_create_kernel: Could not create kernel fast_mean_kernel.
opencl_create_kernel: Could not create kernel fast_variance_kernel.
opencl_create_kernel: Could not create kernel fast_mean_delta_kernel.
opencl_create_kernel: Could not create kernel fast_variance_delta_kernel.
opencl_create_kernel: Could not create kernel flatten_kernel.
opencl_create_kernel: Could not create kernel shortcut_kernel.
opencl_create_kernel: Could not create kernel smooth_l1_kernel.
opencl_create_kernel: Could not create kernel softmax_x_ent_kernel.
opencl_create_kernel: Could not create kernel logistic_x_ent_kernel.
opencl_create_kernel: Could not create kernel l2_kernel.
opencl_create_kernel: Could not create kernel l1_kernel.
opencl_create_kernel: Could not create kernel wgan_kernel.
opencl_create_kernel: Could not create kernel deinter_kernel.
opencl_create_kernel: Could not create kernel inter_kernel.
opencl_create_kernel: Could not create kernel weighted_sum_kernel.
opencl_create_kernel: Could not create kernel weighted_delta_kernel.
opencl_create_kernel: Could not create kernel mult_add_into_kernel.
opencl_create_kernel: Could not create kernel softmax_tree_kernel.
opencl_create_kernel: Could not create kernel softmax_kernel.
opencl_create_kernel: Could not create kernel scale_mask_kernel.
opencl_create_kernel: Could not create kernel dot_kernel.
opencl_create_kernel: Could not create kernel upsample_kernel.
opencl_create_kernel: Could not create kernel gemm_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel col2im_gpu_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel binarize_kernel.
opencl_create_kernel: Could not create kernel binarize_input_kernel.
opencl_create_kernel: Could not create kernel binarize_weights_kernel.
opencl_create_kernel: Could not create kernel smooth_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel im2col_gpu_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel forward_maxpool_layer_kernel.
opencl_create_kernel: Could not create kernel backward_maxpool_layer_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel forward_avgpool_layer_kernel.
opencl_create_kernel: Could not create kernel backward_avgpool_layer_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel levels_image_kernel.
opencl_create_kernel: Could not create kernel forward_crop_layer_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel yoloswag420blazeit360noscopemMmMmMonsterKill.

Any ideas what causes the problem?

Thanks!

Can't build requires xcode-beta path

When I'm running cmake --build build I get this message:

...
[ 33%] Building C object CMakeFiles/bindarknet.dir/examples/darknet.c.o
make[2]: *** No rule to make target `/Applications/Xcode-beta.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/OpenCL.framework', needed by `darknet'.  Stop.
make[1]: *** [CMakeFiles/bindarknet.dir/all] Error 2
make: *** [all] Error 2

OpenCL.framework does exist on Xcode.app, I already tried running sudo xcode-select --switch /Applications/Xcode.app/Contents/Developer but after rebuilding it keeps looking for xcode-beta.app

opencl gemm_kernel error: CL_INVALID_WORK_GROUP_SIZE for the function gemm_offset_gpu() in blas_kernels.c

When I run darknet using the function gemm_offset_gpu() in blas_kernels.c, it occurs the following error:
FATAL ERROR: CL_INVALID_WORK_GROUP_SIZE opencl gemm_kernel error: CL_INVALID_WORK_GROUP_SIZE

How to fix it?

Build + Run errors

Hi @sowson,

First of all thank you for your this amazing work. I'm trying to install on my computer running Ubuntu 18.04, with a RX570. I installed rocm and OpenCL. I had some problems with clBlas instalation following your instructions on MakeFile due I haven't /usr/lib64 folder, on ubuntu 18 this folder don't exist.

Once I run cmake .., and make, instruction make install give me 2 error with files bugfixes.h and unit.h, they don't exist. If I delete the rows regarding this files the instalation works well.

Once all is installed It's impossible run it. All time give me an "Segmentation fault (generated 'core')".

I also tried sudo make on main folder but a lot of errors appears on image_opencv.cpp.o, all these errors says that there are some references without definition.

Please help me, I'm stuck since a week ago.

Thank you in advance.

Support for camera

Hello,
I have built the binary using OpenCV 3.4.11 and it works. However, if I try to use the camera (./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights) the application starts to not respond... it takes a while to load the image, but once loaded, the image displayed never changes although the graphics card is being used. Also, when I try to use a video as an input, I get floating point exception...

Have problems like those happened to someone? Maybe the camera problems are because of low fps (I tested and had like 13fps which is super low... but when using the app I get 1fps and I do not know why), also... any ideas about the floating point exception when trying to process video inputs?

Thank you a lot

can't see Readme

can't use youtube in china

Classifier training behaves different on AMD and Intel GPU

Hello, @sowson , thanks for yolov4 updating.

I got a problem that training behavior are different on two gpus. When training on the AMD Radeon Pro 455, the loss value decrease normally, but when using Intel(R) HD Graphics 530 on the same MacBook pro, the loss value became nan or inf at the first or second batch. I switch the GPU with '-i 0' and '-i 1'.

It's a 2-classes classification , total images are 383. Base model is darknet19.conv.23 extracted from darknet19.weights.

I also trained some yolov3 models on the two gpus, but loss value not differ so much.

Here are training logs:

Device IDs: 2
Device ID: 0
Device name: Intel(R) HD Graphics 530
Device vendor: Intel Inc.
Device opencl availability: OpenCL 1.2
Device opencl used: 1.2(Aug 31 2020 22:26:30)
Device double precision: NO
Device max group size: 256
Device address bits: 64
dogs
1
layer     filters    size              input                output
    0 conv     32  3 x 3 / 1   256 x 256 x   3   ->   256 x 256 x  32  0.113 BFLOPs
    1 max          2 x 2 / 2   256 x 256 x  32   ->   128 x 128 x  32
    2 conv     64  3 x 3 / 1   128 x 128 x  32   ->   128 x 128 x  64  0.604 BFLOPs
    3 max          2 x 2 / 2   128 x 128 x  64   ->    64 x  64 x  64
    4 conv    128  3 x 3 / 1    64 x  64 x  64   ->    64 x  64 x 128  0.604 BFLOPs
    5 conv     64  1 x 1 / 1    64 x  64 x 128   ->    64 x  64 x  64  0.067 BFLOPs
    6 conv    128  3 x 3 / 1    64 x  64 x  64   ->    64 x  64 x 128  0.604 BFLOPs
    7 max          2 x 2 / 2    64 x  64 x 128   ->    32 x  32 x 128
    8 conv    256  3 x 3 / 1    32 x  32 x 128   ->    32 x  32 x 256  0.604 BFLOPs
    9 conv    128  1 x 1 / 1    32 x  32 x 256   ->    32 x  32 x 128  0.067 BFLOPs
   10 conv    256  3 x 3 / 1    32 x  32 x 128   ->    32 x  32 x 256  0.604 BFLOPs
   11 max          2 x 2 / 2    32 x  32 x 256   ->    16 x  16 x 256
   12 conv    512  3 x 3 / 1    16 x  16 x 256   ->    16 x  16 x 512  0.604 BFLOPs
   13 conv    256  1 x 1 / 1    16 x  16 x 512   ->    16 x  16 x 256  0.067 BFLOPs
   14 conv    512  3 x 3 / 1    16 x  16 x 256   ->    16 x  16 x 512  0.604 BFLOPs
   15 conv    256  1 x 1 / 1    16 x  16 x 512   ->    16 x  16 x 256  0.067 BFLOPs
   16 conv    512  3 x 3 / 1    16 x  16 x 256   ->    16 x  16 x 512  0.604 BFLOPs
   17 max          2 x 2 / 2    16 x  16 x 512   ->     8 x   8 x 512
   18 conv   1024  3 x 3 / 1     8 x   8 x 512   ->     8 x   8 x1024  0.604 BFLOPs
   19 conv    512  1 x 1 / 1     8 x   8 x1024   ->     8 x   8 x 512  0.067 BFLOPs
   20 conv   1024  3 x 3 / 1     8 x   8 x 512   ->     8 x   8 x1024  0.604 BFLOPs
   21 conv    512  1 x 1 / 1     8 x   8 x1024   ->     8 x   8 x 512  0.067 BFLOPs
   22 conv   1024  3 x 3 / 1     8 x   8 x 512   ->     8 x   8 x1024  0.604 BFLOPs
   23 conv      2  1 x 1 / 1     8 x   8 x1024   ->     8 x   8 x   2  0.000 BFLOPs
   24 avg                        8 x   8 x   2   ->     2
   25 softmax                                           2
Learning Rate: 0.1, Momentum: 0.9, Decay: 0.0005
383
128 448
Saving weights to dogs/backup/dogs.start.conv.weights
Loaded: 0.000046 seconds
1, 0.334: 13.241982, 13.241982 avg, 0.000000 rate, 47.324300 seconds, 128 images
Loaded: 0.000050 seconds
2, 0.668: nan, nan avg, 0.000000 rate, 61.340651 seconds, 256 images
Loaded: 0.000050 seconds
3, 1.003: nan, nan avg, 0.000000 rate, 61.352529 seconds, 384 images
Saving weights to dogs/backup/dogs_1.weights
Loaded: 0.000044 seconds

And on the AMD GPU:

Device IDs: 2
Device ID: 1
Device name: AMD Radeon Pro 455 Compute Engine
Device vendor: AMD
Device opencl availability: OpenCL 1.2
Device opencl used: 1.2 (Sep 11 2020 22:04:49)
Device double precision: YES
Device max group size: 256
Device address bits: 32
dogs
1
layer     filters    size              input                output
    0 conv     32  3 x 3 / 1   256 x 256 x   3   ->   256 x 256 x  32  0.113 BFLOPs
    1 max          2 x 2 / 2   256 x 256 x  32   ->   128 x 128 x  32
    2 conv     64  3 x 3 / 1   128 x 128 x  32   ->   128 x 128 x  64  0.604 BFLOPs
    3 max          2 x 2 / 2   128 x 128 x  64   ->    64 x  64 x  64
    4 conv    128  3 x 3 / 1    64 x  64 x  64   ->    64 x  64 x 128  0.604 BFLOPs
    5 conv     64  1 x 1 / 1    64 x  64 x 128   ->    64 x  64 x  64  0.067 BFLOPs
    6 conv    128  3 x 3 / 1    64 x  64 x  64   ->    64 x  64 x 128  0.604 BFLOPs
    7 max          2 x 2 / 2    64 x  64 x 128   ->    32 x  32 x 128
    8 conv    256  3 x 3 / 1    32 x  32 x 128   ->    32 x  32 x 256  0.604 BFLOPs
    9 conv    128  1 x 1 / 1    32 x  32 x 256   ->    32 x  32 x 128  0.067 BFLOPs
   10 conv    256  3 x 3 / 1    32 x  32 x 128   ->    32 x  32 x 256  0.604 BFLOPs
   11 max          2 x 2 / 2    32 x  32 x 256   ->    16 x  16 x 256
   12 conv    512  3 x 3 / 1    16 x  16 x 256   ->    16 x  16 x 512  0.604 BFLOPs
   13 conv    256  1 x 1 / 1    16 x  16 x 512   ->    16 x  16 x 256  0.067 BFLOPs
   14 conv    512  3 x 3 / 1    16 x  16 x 256   ->    16 x  16 x 512  0.604 BFLOPs
   15 conv    256  1 x 1 / 1    16 x  16 x 512   ->    16 x  16 x 256  0.067 BFLOPs
   16 conv    512  3 x 3 / 1    16 x  16 x 256   ->    16 x  16 x 512  0.604 BFLOPs
   17 max          2 x 2 / 2    16 x  16 x 512   ->     8 x   8 x 512
   18 conv   1024  3 x 3 / 1     8 x   8 x 512   ->     8 x   8 x1024  0.604 BFLOPs
   19 conv    512  1 x 1 / 1     8 x   8 x1024   ->     8 x   8 x 512  0.067 BFLOPs
   20 conv   1024  3 x 3 / 1     8 x   8 x 512   ->     8 x   8 x1024  0.604 BFLOPs
   21 conv    512  1 x 1 / 1     8 x   8 x1024   ->     8 x   8 x 512  0.067 BFLOPs
   22 conv   1024  3 x 3 / 1     8 x   8 x 512   ->     8 x   8 x1024  0.604 BFLOPs
   23 conv      2  1 x 1 / 1     8 x   8 x1024   ->     8 x   8 x   2  0.000 BFLOPs
   24 avg                        8 x   8 x   2   ->     2
   25 softmax                                           2
Learning Rate: 0.1, Momentum: 0.9, Decay: 0.0005
383
128 448
Saving weights to dogs/backup/dogs.start.conv.weights
Loaded: 0.000053 seconds
1, 0.334: 0.724708, 0.724708 avg, 0.000000 rate, 20.728899 seconds, 128 images
Loaded: 0.000023 seconds
2, 0.668: 0.699131, 0.722151 avg, 0.000000 rate, 28.956159 seconds, 256 images
Loaded: 0.000042 seconds
3, 1.003: 0.740397, 0.723975 avg, 0.000000 rate, 29.074495 seconds, 384 images
Saving weights to dogs/backup/dogs_1.weights
Loaded: 0.000050 seconds
4, 1.337: 0.764463, 0.728024 avg, 0.000000 rate, 21.115983 seconds, 512 images
Loaded: 0.000041 seconds

Error when compile on MacBook Pro 2019

Hello,
I tried to run make but it give me this error :
ld: warning: directory not found for option '-L/usr/lib/x86_64-linux-gnu/'
ld: warning: directory not found for option '-L/usr/lib64'
ld: library not found for -lOpenCL
clang: fatal error: linker command failed with exit code 1 (use -v to see invocation)
make: *** [libdarknet.so] Error 1
Please advise
Thanks

Coun't Predict yolov3 -- opencl error: CL_INVALID_KERNEL

It didn't have any issues while compiling. But when i run this command - ./darknet detect cfg/yolov3-tiny.cfg yolov3-tiny.weights data/dog.jpg command line output is as follows.

Device ID: 0
Device name: Intel(R) HD Graphics IvyBridge M GT2
Device vendor: Intel
Device opencl availability: OpenCL 1.2 beignet 1.1.1
Device opencl used: 1.1.1
Device double precision: YES
Device max group size: 512
Device address bits: 32
opencl_load: could not compile. error: CL_COMPILE_PROGRAM_FAILURE
CL_PROGRAM_BUILD_LOG:
stringInput.cl:1:1469: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:2952: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:2974: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:2981: error: double precision constant requires cl_khr_fp64, casting to single precision

opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel activate_array_kernel.
opencl_create_kernel: Could not create kernel gradient_array_kernel.
opencl_load: could not compile. error: CL_COMPILE_PROGRAM_FAILURE
CL_PROGRAM_BUILD_LOG:
stringInput.cl:1:8278: error: double precision constant requires cl_khr_fp64, casting to single precision

opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel test_kernel.
opencl_create_kernel: Could not create kernel softmax_device.
opencl_create_kernel: Could not create kernel scale_bias_kernel.
opencl_create_kernel: Could not create kernel backward_scale_kernel.
opencl_create_kernel: Could not create kernel add_bias_kernel.
opencl_create_kernel: Could not create kernel backward_bias_kernel.
opencl_create_kernel: Could not create kernel adam_kernel.
opencl_create_kernel: Could not create kernel normalize_kernel.
opencl_create_kernel: Could not create kernel normalize_delta_kernel.
opencl_create_kernel: Could not create kernel l2norm_kernel.
opencl_create_kernel: Could not create kernel variance_delta_kernel.
opencl_create_kernel: Could not create kernel accumulate_kernel.
opencl_create_kernel: Could not create kernel mean_delta_kernel.
opencl_create_kernel: Could not create kernel mean_kernel.
opencl_create_kernel: Could not create kernel variance_kernel.
opencl_create_kernel: Could not create kernel reorg_kernel.
opencl_create_kernel: Could not create kernel axpy_kernel.
opencl_create_kernel: Could not create kernel pow_kernel.
opencl_create_kernel: Could not create kernel const_kernel.
opencl_create_kernel: Could not create kernel constrain_kernel.
opencl_create_kernel: Could not create kernel supp_kernel.
opencl_create_kernel: Could not create kernel add_kernel.
opencl_create_kernel: Could not create kernel scal_kernel.
opencl_create_kernel: Could not create kernel fill_kernel.
opencl_create_kernel: Could not create kernel mask_kernel.
opencl_create_kernel: Could not create kernel copy_kernel.
opencl_create_kernel: Could not create kernel mul_kernel.
opencl_create_kernel: Could not create kernel fast_mean_kernel.
opencl_create_kernel: Could not create kernel fast_variance_kernel.
opencl_create_kernel: Could not create kernel fast_mean_delta_kernel.
opencl_create_kernel: Could not create kernel fast_variance_delta_kernel.
opencl_create_kernel: Could not create kernel flatten_kernel.
opencl_create_kernel: Could not create kernel shortcut_kernel.
opencl_create_kernel: Could not create kernel smooth_l1_kernel.
opencl_create_kernel: Could not create kernel softmax_x_ent_kernel.
opencl_create_kernel: Could not create kernel logistic_x_ent_kernel.
opencl_create_kernel: Could not create kernel l2_kernel.
opencl_create_kernel: Could not create kernel l1_kernel.
opencl_create_kernel: Could not create kernel wgan_kernel.
opencl_create_kernel: Could not create kernel deinter_kernel.
opencl_create_kernel: Could not create kernel inter_kernel.
opencl_create_kernel: Could not create kernel weighted_sum_kernel.
opencl_create_kernel: Could not create kernel weighted_delta_kernel.
opencl_create_kernel: Could not create kernel mult_add_into_kernel.
opencl_create_kernel: Could not create kernel softmax_tree_kernel.
opencl_create_kernel: Could not create kernel softmax_kernel.
opencl_create_kernel: Could not create kernel scale_mask_kernel.
opencl_create_kernel: Could not create kernel dot_kernel.
opencl_create_kernel: Could not create kernel upsample_kernel.
opencl_create_kernel: Could not create kernel gemm_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel col2im_gpu_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel binarize_kernel.
opencl_create_kernel: Could not create kernel binarize_input_kernel.
opencl_create_kernel: Could not create kernel binarize_weights_kernel.
opencl_create_kernel: Could not create kernel smooth_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel im2col_gpu_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel forward_maxpool_layer_kernel.
opencl_create_kernel: Could not create kernel backward_maxpool_layer_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel forward_avgpool_layer_kernel.
opencl_create_kernel: Could not create kernel backward_avgpool_layer_kernel.
opencl_load: could not compile. error: CL_COMPILE_PROGRAM_FAILURE
CL_PROGRAM_BUILD_LOG:
stringInput.cl:1:1537: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:2708: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:2714: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:2793: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:2799: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:3003: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:3210: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:3282: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:3354: error: double precision constant requires cl_khr_fp64, casting to single precision
stringInput.cl:1:3714: error: double precisio
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel levels_image_kernel.
opencl_create_kernel: Could not create kernel forward_crop_layer_kernel.
opencl_load: could not link. error: CL_INVALID_LINKER_OPTIONS
CL_PROGRAM_BUILD_LOG:

opencl_create_kernel: Could not create kernel yoloswag420blazeit360noscopemMmMmMonsterKill.
layer filters size input output
0 conv 16 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 16 0.150 BFLOPs
1 max 2 x 2 / 2 416 x 416 x 16 -> 208 x 208 x 16
2 conv 32 3 x 3 / 1 208 x 208 x 16 -> 208 x 208 x 32 0.399 BFLOPs
3 max 2 x 2 / 2 208 x 208 x 32 -> 104 x 104 x 32
4 conv 64 3 x 3 / 1 104 x 104 x 32 -> 104 x 104 x 64 0.399 BFLOPs
5 max 2 x 2 / 2 104 x 104 x 64 -> 52 x 52 x 64
6 conv 128 3 x 3 / 1 52 x 52 x 64 -> 52 x 52 x 128 0.399 BFLOPs
7 max 2 x 2 / 2 52 x 52 x 128 -> 26 x 26 x 128
8 conv 256 3 x 3 / 1 26 x 26 x 128 -> 26 x 26 x 256 0.399 BFLOPs
9 max 2 x 2 / 2 26 x 26 x 256 -> 13 x 13 x 256
10 conv 512 3 x 3 / 1 13 x 13 x 256 -> 13 x 13 x 512 0.399 BFLOPs
11 max 2 x 2 / 1 13 x 13 x 512 -> 13 x 13 x 512
12 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
13 conv 256 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 256 0.089 BFLOPs
14 conv 512 3 x 3 / 1 13 x 13 x 256 -> 13 x 13 x 512 0.399 BFLOPs
15 conv 255 1 x 1 / 1 13 x 13 x 512 -> 13 x 13 x 255 0.044 BFLOPs
16 yolo
17 route 13
18 conv 128 1 x 1 / 1 13 x 13 x 256 -> 13 x 13 x 128 0.011 BFLOPs
19 upsample 2x 13 x 13 x 128 -> 26 x 26 x 128
20 route 19 8
21 conv 256 3 x 3 / 1 26 x 26 x 384 -> 26 x 26 x 256 1.196 BFLOPs
22 conv 255 1 x 1 / 1 26 x 26 x 256 -> 26 x 26 x 255 0.088 BFLOPs
23 yolo
Loading weights from yolov3-tiny.weights...Done!
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl_kernel could not set kernel argument. error: CL_INVALID_KERNEL
opencl error: CL_INVALID_KERNEL
data/dog.jpg: Predicted in 1.541940 seconds.

Slow Perfomance on Mali-T628

I just tested this darknet version on an Mali-T628 GPU (ODroid XU4). It should be capable to reach 122 GFLOPS.

Device ID: 0
Device name: Mali-T628
Device vendor: ARM
Device opencl availability: OpenCL 1.2 v1.r12p0-04rel0.03af15950392f3702b248717f4938b82
Device opencl used: 1.2
Device double precision: YES
Device max group size: 256
Device address bits: 64

I tested the yolov3-tiny network and the stats are as following:

first iteration: 14.11 seconds
second iteration: 7.29 seconds.
1~2 second if running on the CPU

Any hints? Do you have any benchmark results for the RaspberryPi?
Thanks!

error: Compiler frontend failed (error code 59)

Hi, I was trying to train a classifier on CIFAR-10( https://pjreddie.com/darknet/train-cifar/). but i had a problem. I tried to compile a darknet on Odroid XU4(Mali T628). but I couldn't.
This is my error.


Device IDs: 2
Device ID: 0
Device name: Mali-T628
Device vendor: ARM
Device opencl availability: OpenCL 1.2 v1.r17p0-01rel0.a881d28363cdb20f0017ed13c980967e
Device opencl used: 1.2
Device double precision: YES
Device max group size: 256
Device address bits: 64
opencl_load: could not compile. error: CL_UNKNOWN_ERROR
CL_PROGRAM_BUILD_LOG:
<source>:1:975: error: Using 'atom_cmpxchg' function requires the extension 'cl_khr_global_int32_base_atomics' to be enabled

error: Compiler frontend failed (error code 59)

CODE:
__kernel void test_kernel(int N, __global float *input, __global float *output, __global float *expected) { int index = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; output[index] = sqrt(input[index]); index += 1; input[index] = output[index-1]; output[index] = log(input[index]); index += 1; input[index] = output[index-1]; output[index] = pow(input[index], output[index-2]); index += 1; input[index] = output[index-1]; output[index] = -exp(input[index]); index += 1; input[index] = output[index-1]; output[index] = fabs(input[index]); index += 1; input[index] = output[index-1]; output[index] = sin(input[index]); index += 1; input[index] = output[index-1]; output[index] = cos(input[index]); } static void atomicAdd(volatile __global float *a, float v) { union { float f; unsigned int i; } o; o.i = 0; union { float f; unsigned int i; } n; n.i = 1; do { o.f = *a; n.f = o.f + v; } while (atom_cmpxchg((__global unsigned int *)a, o.i, n.i) != o.i); } __kernel void scale_bias_kernel(int N, __global float *output, __global float *biases, int batch, int n, int size) { int index = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int i = (index % (n*size) / size); output[index] *= biases[i]; } __kernel void backward_scale_kernel(int tuning, __local float* sums, int batch, int n, int size, __global float *x_norm, __global float *delta, __global float *scale_updates) { int t = get_global_id(0); if (t > tuning) return; int i = get_global_id(1); if (i > n) return; sums[t] = 0; int k,j,s; for(j = 0; j < batch; ++j){ for(k = t; k < size; k += tuning){ int index = size*i + size*n*j + k + t; sums[t] += delta[index]*x_norm[index]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { for(s = 0; s < tuning; ++s) { scale_updates[i] += sums[s]; } } } __kernel void add_bias_kernel(int N, __global float *output, __global float *biases, int batch, int n, int size) { int index = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int i = (index % (n*size) / size); output[index] += biases[i]; } __kernel void backward_bias_kernel(int tuning, __local float* sums, int batch, int n, int size, __global float *bias_updates, __global float *delta) { int t = get_global_id(0); if (t > tuning) return; int i = get_global_id(1); if (i > n) return; sums[t] = 0; int k,j,s; for(j = 0; j < batch; ++j){ for(k = t; k < size; k += tuning){ int index = size*i + size*n*j + k + t; sums[t] += delta[index]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { for(s = 0; s < tuning; ++s) { bias_updates[i] += sums[s]; } } } __kernel void mean_kernel(int N, __global float *x, int batch, int filters, int spatial, __global float *mean) { float scale = 1.f/(batch * spatial); int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; mean[i] = 0; int j, k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; mean[i] += x[index]; } } mean[i] *= scale; } __kernel void variance_kernel(int N, __global float *x, __global float *mean, int batch, int filters, int spatial, __global float *variance) { float scale = 1.f/(batch * spatial - 1); int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; variance[i] = 0; int j,k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; variance[i] += pow((x[index] - mean[i]), 2); } } variance[i] *= scale; } __kernel void mean_delta_kernel(int N, __global float *delta, __global float *variance, int batch, int filters, int spatial, __global float *mean_delta) { int id = (get_group_id(0) + get_group_id(1) * get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; mean_delta[i] = 0; int j, k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; mean_delta[i] += delta[index]; } } mean_delta[i] *= (-1.f/sqrt(variance[i] + .00001f)); } __kernel void variance_delta_kernel(int N, __global float *x, __global float *delta, __global float *mean, __global float *variance, int batch, int filters, int spatial, __global float *variance_delta) { int id = (get_group_id(0) + get_group_id(1) * get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; variance_delta[i] = 0; int j,k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; variance_delta[i] += delta[index] * (x[index] - mean[i]); } } variance_delta[i] *= -.5f * pow(variance[i] + .00001f, (float)(-3.f/2.f)); } __kernel void accumulate_kernel(__global float *x, int n, int groups, __global float *sum) { int k; int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (i >= groups) return; sum[i] = 0; for(k = 0; k < n; ++k){ sum[i] += x[k*groups + i]; } } __kernel void fast_mean_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *x, __global float *mean) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j, k, s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += x[index]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { mean[i] = 0; for (s = 0; s < tuning; ++s) { mean[i] += sums[s]; } mean[i] /= (spatial * batch); } } __kernel void fast_variance_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *x, __global float *mean, __global float *variance) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j,k,s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += pow((x[index] - mean[i]), 2); } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { variance[i] = 0; for (s = 0; s < tuning; ++s) { variance[i] += sums[s]; } variance[i] /= (spatial * batch - 1); } } __kernel void fast_mean_delta_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *variance, __global float *delta, __global float *mean_delta) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j,k,s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += delta[index]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { mean_delta[i] = 0; for (s = 0; s < tuning; ++s) { mean_delta[i] += sums[s]; } mean_delta[i] *= (-1.f/sqrt(variance[i] + .00001f)); } } __kernel void fast_variance_delta_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *x, __global float *variance, __global float *delta, __global float *mean, __global float *variance_delta) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j,k,s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += delta[index] * (x[index] - mean[i]); } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { variance_delta[i] = 0; for (s = 0; s < tuning; ++s) { variance_delta[i] += sums[s]; } variance_delta[i] *= -.5f * pow(variance[i] + .00001f, (float)(-3.f/2.f)); } } __kernel void adam_kernel(int N, __global float *x, __global float *m, __global float *v, float B1, float B2, float rate, float eps, int t) { int index = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; x[index] = x[index] + (rate * sqrt(1.f-pow(B2, t)) / (1.f-pow(B1, t)) * m[index] / (sqrt((v[index] + eps)))); } __kernel void normalize_kernel(int N, __global float *x, __global float *mean, __global float *variance, int batch, int filters, int spatial) { int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int b = (id / (filters*spatial)); int f = (id % (filters*spatial) / spatial); int i = (id % spatial); int index = b*filters*spatial + f*spatial + i; x[index] = (x[index] - mean[f])/(sqrt(variance[f] + .00001f)); } __kernel void normalize_delta_kernel(int N, __global float *x, __global float *mean, __global float *variance, __global float *mean_delta, __global float *variance_delta, int batch, int filters, int spatial, __global float *delta) { int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int j = (id / (filters*spatial)); int f = (id % (filters*spatial) / spatial); int k = (id % spatial); int index = j*filters*spatial + f*spatial + k; delta[index] = delta[index] * 1.f/(sqrt(variance[f] + .00001f)) + variance_delta[f] * 2. * (x[index] - mean[f]) / (spatial * batch) + mean_delta[f]/(spatial*batch); } __kernel void l2norm_kernel(int N, __global float *x, __global float *dx, int batch, int filters, int spatial) { int index = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int b = index / spatial; int i = index % spatial; int f; float sum = 0; for(f = 0; f < filters; ++f){ int index = b*filters*spatial + f*spatial + i; sum += pow(x[index], 2.f); } sum = sqrt(sum); if(sum == 0) sum = 1.f; for(f = 0; f < filters; ++f){ int index = b*filters*spatial + f*spatial + i; x[index] /= sum; dx[index] = (1 - x[index]) / sum; } } __kernel void reorg_kernel(int N, __global float *x, int w, int h, int c, int batch, int stride, int forward, __global float *out) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i >= N) return; int in_index = i; int in_w = i%w; i = i/w; int in_h = i%h; i = i/h; int in_c = i%c; i = i/c; int b = i%batch; int out_c = c/(stride*stride); int c2 = in_c % out_c; int offset = in_c / out_c; int w2 = in_w*stride + offset % stride; int h2 = in_h*stride + offset / stride; int out_index = w2 + w*stride*(h2 + h*stride*(c2 + out_c*b)); if(forward) out[out_index] = x[in_index]; else out[in_index] = x[out_index]; } __kernel void axpy_kernel(int N, __const float ALPHA, __global float *X, int OFFX, int INCX, __global float *Y, int OFFY, int INCY) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[i*INCY+OFFY] += ALPHA*X[i*INCX+OFFX]; } __kernel void pow_kernel(int N, __const float ALPHA, __global float *X, int OFFX, int INCX, __global float *Y, int OFFY, int INCY) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[i*INCY + OFFY] = pow(X[i*INCX + OFFX], ALPHA); } __kernel void const_kernel(int N, __const float ALPHA, __global float *X, int OFFX, int INCX) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[i*INCX + OFFX] = ALPHA; } __kernel void constrain_kernel(int N, __const float ALPHA, __global float *X, int INCX) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[i*INCX] = min(ALPHA, max(-ALPHA, X[i*INCX])); } __kernel void supp_kernel(int N, __const float ALPHA, __global float *X, int INCX) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) { if((X[i*INCX] * X[i*INCX]) < (ALPHA * ALPHA)) X[i*INCX] = 0; } } __kernel void add_kernel(int N, __const float ALPHA, __global float *X, int INCX) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[i*INCX] += ALPHA; } __kernel void scal_kernel(int N, __const float ALPHA, __global float *X, int INCX) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[i*INCX] *= ALPHA; } __kernel void fill_kernel(int N, __const float ALPHA, __global float *X, int OFFX, int INCX) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[i*INCX + OFFX] = ALPHA; } __kernel void mask_kernel(int n, __global float *x, float mask_num, __global float *mask, float val) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n && mask[i] == mask_num) x[i] = val; } __kernel void copy_kernel(int N, __global float *X, int OFFX, int INCX, __global float *Y, int OFFY, int INCY) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[i*INCY + OFFY] = X[i*INCX + OFFX]; } __kernel void mul_kernel(int N, __global float *X, int INCX, __global float *Y, int INCY) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[i*INCY] *= X[i*INCX]; } __kernel void flatten_kernel(int N, __global float *x, int spatial, int layers, int batch, int forward, __global float *out) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i >= N) return; int in_s = i%spatial; i = i/spatial; int in_c = i%layers; i = i/layers; int b = i; int i1 = b*layers*spatial + in_c*spatial + in_s; int i2 = b*layers*spatial + in_s*layers + in_c; if (forward) out[i2] = x[i1]; else out[i1] = x[i2]; } __kernel void shortcut_kernel(int size, int minw, int minh, int minc, int stride, int sample, int batch, int w1, int h1, int c1, __global float *add, int w2, int h2, int c2, float s1, float s2, __global float *out) { int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= size) return; int i = id % minw; id /= minw; int j = id % minh; id /= minh; int k = id % minc; id /= minc; int b = id % batch; int out_index = i*sample + w2*(j*sample + h2*(k + c2*b)); int add_index = i*stride + w1*(j*stride + h1*(k + c1*b)); out[out_index] = s1*out[out_index] + s2*add[add_index]; } __kernel void smooth_l1_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float diff = truth[i] - pred[i]; float abs_val = fabs(diff); if(abs_val < 1) { error[i] = diff * diff; delta[i] = diff; } else { error[i] = 2*abs_val - 1; delta[i] = (diff > 0) ? 1 : -1; } } } __kernel void softmax_x_ent_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n) { float t = truth[i]; float p = pred[i]; error[i] = (t!=0) ? -log(p) : 0; delta[i] = t-p; } } __kernel void logistic_x_ent_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float t = truth[i]; float p = pred[i]; error[i] = -t*log(p+.0000001f) - (1.f-t)*log(1.f-p+.0000001f); delta[i] = t-p; } } __kernel void l2_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float t = truth[i]; float p = pred[i]; float diff = t-p; error[i] = pow(diff,2); delta[i] = diff; } } __kernel void l1_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float diff = truth[i] - pred[i]; error[i] = fabs(diff); delta[i] = (diff > 0) ? 1 : -1; } } __kernel void wgan_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ error[i] = (truth[i]!=0) ? -pred[i] : pred[i]; delta[i] = (truth[i] > 0) ? 1 : -1; } } __kernel void weighted_sum_kernel(int n, __global float *a, __global float *b, __global float *s, __global float *c) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ c[i] = s[i]*a[i] + (1-s[i])*(b ? b[i] : 0); } } __kernel void weighted_delta_kernel(int n, __global float *a, __global float *b, __global float *s, __global float *da, __global float *db, __global float *ds, __global float *dc) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ if(da) da[i] += dc[i] * s[i]; db[i] += dc[i] * (1-s[i]); ds[i] += dc[i] * a[i] + dc[i] * -b[i]; } } __kernel void mult_add_into_kernel(int n, __global float *a, __global float *b, __global float *c) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ c[i] += a[i]*b[i]; } } __kernel void deinter_kernel(int NX, __global float *X, int NY, __global float *Y, int B, __global float *OUT) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < (NX+NY)*B){ int b = i / (NX+NY); int j = i % (NX+NY); if (j < NX){ if(X) X[b*NX + j] += OUT[i]; } else { if(Y) Y[b*NY + j - NX] += OUT[i]; } } } __kernel void inter_kernel(int NX, __global float *X, int NY, __global float *Y, int B, __global float *OUT) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < (NX+NY)*B){ int b = i / (NX+NY); int j = i % (NX+NY); if (j < NX){ OUT[i] = X[b*NX + j]; } else { OUT[i] = Y[b*NY + j - NX]; } } } __kernel void softmax_device(__global float *input, int n, float temp, int stride, __global float *output) { int i; float sum = 0; float largest = -FLT_MAX; for(i = 0; i < n; ++i){ int val = input[i*stride]; largest = (val>largest) ? val : largest; } for(i = 0; i < n; ++i){ float e = exp(input[i*stride]/temp - largest/temp); sum += e; output[i*stride] = e; } for(i = 0; i < n; ++i){ output[i*stride] /= sum; } } __kernel void softmax_kernel(__global float *input, int offset, int n, int batch, int batch_offset, int groups, int group_offset, int stride, float temp, __global float *output) { int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= batch*groups) return; int b = id / groups; int g = id % groups; softmax_device(input + b*batch_offset + g*group_offset + offset, n, temp, stride, output + b*batch_offset + g*group_offset + offset); } __kernel void softmax_tree_kernel(__global float *input, int offset, int index, int spatial, int batch, int stride, float temp, __global float *output, int groups, __global float *group_size, __global float *group_offset) { int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= spatial*batch*groups) return; int s = id % spatial; id = id / spatial; int g = id % groups; int b = id / groups; int goff = group_offset[g]*spatial; int boff = b*stride; softmax_device(input + offset + goff + boff + s, group_size[g], temp, spatial, output + offset + goff + boff + s); } __kernel void scale_mask_kernel(int n, __global float *x, float mask_num, __global float *mask, float scale) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n && mask[i] == mask_num) x[i] *= scale; } __kernel void dot_kernel(__global float *output, float scale, int batch, int n, int size, __global float *delta) { int index = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); int f1 = index / n; int f2 = index % n; if (f2 <= f1) return; float sum = 0; float norm1 = 0; float norm2 = 0; int b, i; for(b = 0; b < batch; ++b){ for(i = 0; i < size; ++i){ int i1 = b * size * n + f1 * size + i; int i2 = b * size * n + f2 * size + i; sum += output[i1] * output[i2]; norm1 += output[i1] * output[i1]; norm2 += output[i2] * output[i2]; } } norm1 = sqrt(fabs(norm1)); norm2 = sqrt(fabs(norm2)); float norm = norm1 * norm2; sum = sum / norm; for(b = 0; b < batch; ++b){ for(i = 0; i < size; ++i){ int i1 = b * size * n + f1 * size + i; int i2 = b * size * n + f2 * size + i; delta[i1] += - scale * sum * output[i2] / norm; delta[i2] += - scale * sum * output[i1] / norm; } } } __kernel void upsample_kernel(int N, __global float *x, int w, int h, int c, int batch, int stride, int forward, float scale, __global float *out) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i >= N) return; int out_index = i; int out_w = i%(w*stride); i = i/(w*stride); int out_h = i%(h*stride); i = i/(h*stride); int out_c = i%c; i = i/c; int b = i%batch; int in_w = out_w / stride; int in_h = out_h / stride; int in_c = out_c; int in_index = b*w*h*c + in_c*w*h + in_h*w + in_w; if(forward) out[out_index] += scale * x[in_index]; else atomicAdd(&x[in_index], scale * out[out_index]); } __kernel void gemm_kernel( int tuning, __local float* sums, int TA, int TB, int M, int N, int K, __const float ALPHA, __global float *A, int offset_A, int lda, __global float *B, int offset_B, int ldb, __const float BETA, __global float *C, int offset_C, int ldc) { int td = get_global_id(0); if (td > tuning) return; int id = get_global_id(1); if (id > N*M) return; int iM = id / N; int jN = id % N; int kK = 0; int ts = 0; C[iM * ldc + jN + offset_C] *= BETA; sums[td] = 0; for(kK = td; kK < K; kK += tuning) { if (TA==0 && TB==0) { sums[td] += ALPHA * A[iM * lda + kK + offset_A] * B[kK * ldb + jN + offset_B]; } else if (TA==1 && TB==0) { sums[td] += ALPHA * A[kK * lda + iM + offset_A] * B[kK * ldb + jN + offset_B]; } else if (TA==0 && TB==1) { sums[td] += ALPHA * A[iM * lda + kK + offset_A] * B[jN * ldb + kK + offset_B]; } else { sums[td] += ALPHA * A[iM + kK * lda + offset_A] * B[kK + jN * ldb + offset_B]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (td == tuning-1) { for(ts = 0; ts < tuning; ++ts) { if (TA==0 && TB==0) { C[iM * ldc + jN + offset_C] += sums[ts]; } else if (TA==1 && TB==0) { C[iM * ldc + jN + offset_C] += sums[ts]; } else if (TA==0 && TB==1) { C[iM * ldc + jN + offset_C] += sums[ts]; } else { C[iM * ldc + jN + offset_C] += sums[ts]; } } } }

and this is option when i compiled.

GPU=1
GPU_FAST=1
GPU_MULTI=0
OPENCV=1
OPENMP=1

NVIDIA=0
AMD=0
ARM=1

I am not familiar with darkent code.
Can you tell what I can change to fix this?

Thanks for the help.

Crash when resizing during training

I have tried training a few different yolov3 models without any success. When trying to train VOC or tiny coco model I crash when the resizing is done in train_detector. The crash in in opencl_push_int_array() with an error from clEnqueueMapBuffer() of CL_INVALID_COMMAND_QUEUE. I can get a model with the coco cfg file, however when testing it the results are incorrect (lots of high probability regions found that are of the wrong class and no detections with the correct class). If I run the same on CUDA, it is working correctly. This was done on both GeForce GT 730 and GTX 108 and an AMD GPU. When reading through some of the allocation code it looks like some of the wrong array names were used. Here are the changes I made. Unfortunately they didn't fix my issue, but thought I'd pass them on in case they really are typos.
diff.txt

Running Issue Error

Hello!
I've faced with several problems, I've already left a comment under your post on your website.
I use BeagleBone AI and have my own trained YOLOv4 model. I've instaled Darknet in OpenCL as in your guide.
Then I try to run the detection using following command : ./darknet detector demo cfg/obj.data cfg/yolov4-obj.cfg /weights/yolov4.weights video1.mp4
And CCL shows the following respond: TIOCL WARNING: Opening Linux shared memory: No such file or Directory.
TIOCL FATAL: The TI Multicore Tools daemon (/usr/bin/ti-mctd) is not running. To start daemon, rm /dev/shm/HeapManager (if exists); ti-mctd. Re-run application. Refer User Guide for details. Aborted.

Don't know what is happening and how to fix this problem. Can you explain/help me to solve this problem??

rebase work

Hi! Thanks for your wonderful work enabling OpenCL for darknet.
Any possibility that you rebase your work on the https://github.com/AlexeyAB/darknet fork? It is much more maintained, it will be (maybe) the reference darknet implementation now that the pjreddie original one points to that and also there is a huge chance that your work might be accepted upstream!

How my network can be convergent quickly ?

Hi @sowson ,

I have trained my network based on issue "Please kindly help us about not convergent network", after 412 rounds the "obj" still keep on one low value (0.00xxx), so how can I make it convergent quickly ? And I see you have trained this network before, how many round did your network can be convergent to < 5.0 avg ? Thanks

clrng doesn't seem to exist in homebrew ?

I'm using the latest MacOS El Captain. I have the newest Homebrew too.

brew install clrng

^^^ there doesn't seem to exist. Did you have to add additional Homebrew tap to get it?

BTW: maybe it's related:

The directory where the SDK links is supposed to be doesn't have the .sdk directory at all.
I've made a symlink anyway, but could you maybe show me the content of your directory on Mac?

[02:08:01][host:/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk]$ la
total 0
drwxr-xr-x  8 root  wheel   256 Dec 31 02:07 ./
drwxr-xr-x  4 root  wheel   128 Dec 31 01:03 ../
-rw-r--r--  1 root  wheel   127 Aug 17 16:45 Entitlements.plist
lrwxr-xr-x  1 root  wheel    15 Dec 31 02:07 MacOSX10.13.sdk@ -> MacOSX10.14.sdk
-rw-r--r--  1 root  wheel  1150 Aug 17 16:45 SDKSettings.json
-rw-r--r--  1 root  wheel  1326 Aug 17 16:45 SDKSettings.plist
drwxr-xr-x  3 root  wheel    96 Oct 18 05:52 System/
drwxr-xr-x  7 root  wheel   224 Oct 18 05:52 usr/

Feedback would be appreciated.

Errors when compile the project: undefined reference to 'avg_predictions'

When I try to compile this project on Ubuntu18.04. It goes wrong and show the error--- undefined reference to 'avg_predictions', which is shown as following:

@sowson How to fix it?

YoloV4 MISH Activation Function and/or Gradient Function Issue

Hello, I am putting this issue for all who follow this repo... do you know any better MISH implementations? I found that in my YOLO4 elements (most but not all, to not break compatibility) this function makes trouble and "nan" values, once in yolov4*.cfg files I will change from "mish" to "leaky" all is fine and training is super stable, I expected detections will be also... but I was wonder about how and why implementation of MISH should be...? Thx for any suggestions!

wrong dimensions from yolov3

Hello All,

currently I import the yolov3.onnx model to onnx v1.1.0 but it have below issues:

there are 2 input, and the dimensions 2 and 3 of 2 inputs is always -1
input 1:
dim 2=-1
dim 3=-1
input 2:
dim 2=-1
dim 3=-1

when importing yolov2.onnx model to onnx v1.1.0, the dimensions is always as below:
dim 2=416
dim 3=416

I don't know what is "-1" mean, and how to show correct dimensions.
so Please help me to detect the issue with my problem

Thanks

Is it possible to run it on Intel GPUs?

Hello,
I have been trying to build it for a computer with only the integrated Intel GPU. I am not able to see the option in the Makefile, so maybe there is no support for it.... could please someone confirm it or, in case there is the possibility of running it only using the integrated GPU, give some information on how to do it?

Thanks a lot!

Installing YOLOv4 windows AMD

Is this already available for windows? if so, is there a tutorial on how to install

crashes on android environment

Project compiles but crashes when executing on Android environment. How find out why it is crashing and then fix it

error while compiling

cc1: note: unrecognized command-line option ‘-Wno-return-type-c-linkage’ may have been intended to silence earlier diagnostics
[ 24%] Building C object CMakeFiles/bindarknet.dir/examples/voxel.c.o
[ 25%] Building C object CMakeFiles/bindarknet.dir/examples/writing.c.o
[ 25%] Building C object CMakeFiles/bindarknet.dir/examples/yolo.c.o
[ 26%] Building C object CMakeFiles/bindarknet.dir/src/yolo_layer.c.o
[ 26%] Building C object CMakeFiles/bindarknet.dir/src/yolo4_layer.c.o
[ 26%] Building C object CMakeFiles/bindarknet.dir/src/gaussian_yolo4_layer.c.o
[ 27%] Building C object CMakeFiles/bindarknet.dir/src/upsample_layer.c.o
[ 27%] Building C object CMakeFiles/bindarknet.dir/src/logistic_layer.c.o
[ 28%] Building C object CMakeFiles/bindarknet.dir/src/l2norm_layer.c.o
[ 28%] Building C object CMakeFiles/bindarknet.dir/src/activation_kernels.c.o
[ 28%] Building C object CMakeFiles/bindarknet.dir/src/avgpool_layer_kernels.c.o
[ 29%] Building C object CMakeFiles/bindarknet.dir/src/blas_kernels.c.o
[ 29%] Building C object CMakeFiles/bindarknet.dir/src/col2im_kernels.c.o
[ 30%] Building C object CMakeFiles/bindarknet.dir/src/convolutional_kernels.c.o
[ 30%] Building C object CMakeFiles/bindarknet.dir/src/crop_layer_kernels.c.o
[ 30%] Building C object CMakeFiles/bindarknet.dir/src/deconvolutional_kernels.c.o
[ 31%] Building C object CMakeFiles/bindarknet.dir/src/dropout_layer_kernels.c.o
[ 31%] Building C object CMakeFiles/bindarknet.dir/src/im2col_kernels.c.o
[ 32%] Building C object CMakeFiles/bindarknet.dir/src/maxpool_layer_kernels.c.o
[ 32%] Building C object CMakeFiles/bindarknet.dir/src/opencl.c.o
[ 32%] Building CXX object CMakeFiles/bindarknet.dir/src/image_opencv.cpp.o
[ 33%] Building C object CMakeFiles/bindarknet.dir/examples/darknet.c.o
[ 33%] Linking CXX executable darknet
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activations.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activations.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activations.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activations.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activations.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activations.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/art.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/art.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/art.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/art.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/art.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/art.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/attention.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/attention.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/attention.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/attention.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/attention.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/attention.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/batchnorm_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/batchnorm_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/batchnorm_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/batchnorm_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/batchnorm_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/batchnorm_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/box.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/box.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/box.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/box.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/box.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/box.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/captcha.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/captcha.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/captcha.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/captcha.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/captcha.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/captcha.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cifar.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cifar.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cifar.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cifar.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cifar.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cifar.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/classifier.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/classifier.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/classifier.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/classifier.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/classifier.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/classifier.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/coco.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/coco.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/coco.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/coco.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/coco.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/coco.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/compare.c.o:(.bss+0x8): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/compare.c.o:(.bss+0x10): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/compare.c.o:(.bss+0x18): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/compare.c.o:(.bss+0x20): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/compare.c.o:(.bss+0x28): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/compare.c.o:(.bss+0x30): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/connected_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/connected_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/connected_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/connected_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/connected_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/connected_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/cost_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/cost_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/cost_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/cost_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/cost_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/cost_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crnn_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crnn_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crnn_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crnn_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crnn_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crnn_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/data.c.o:(.bss+0x28): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/data.c.o:(.bss+0x30): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/data.c.o:(.bss+0x38): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/data.c.o:(.bss+0x40): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/data.c.o:(.bss+0x48): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/data.c.o:(.bss+0x50): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/demo.c.o:(.bss+0x8): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/demo.c.o:(.bss+0x10): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/demo.c.o:(.bss+0x18): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/demo.c.o:(.bss+0x20): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/demo.c.o:(.bss+0x28): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/demo.c.o:(.bss+0x30): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/detection_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/detection_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/detection_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/detection_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/detection_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/detection_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/detector.c.o:(.bss+0x90): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/detector.c.o:(.bss+0x98): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/detector.c.o:(.bss+0xa0): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/detector.c.o:(.bss+0xa8): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/detector.c.o:(.bss+0xb0): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/detector.c.o:(.bss+0xb8): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/dice.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/dice.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/dice.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/dice.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/dice.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/dice.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gemm.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gemm.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gemm.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gemm.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gemm.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gemm.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/go.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/go.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/go.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/go.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/go.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/go.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gru_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gru_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gru_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gru_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gru_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gru_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image.c.o:(.bss+0x8): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image.c.o:(.bss+0x10): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image.c.o:(.bss+0x18): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image.c.o:(.bss+0x20): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image.c.o:(.bss+0x28): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image.c.o:(.bss+0x30): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/iseg_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/iseg_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/iseg_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/iseg_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/iseg_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/iseg_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/instance-segmenter.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/instance-segmenter.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/instance-segmenter.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/instance-segmenter.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/instance-segmenter.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/instance-segmenter.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/list.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/list.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/list.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/list.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/list.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/list.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/local_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/local_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/local_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/local_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/local_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/local_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/lstm_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/lstm_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/lstm_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/lstm_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/lstm_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/lstm_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/lsd.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/lsd.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/lsd.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/lsd.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/lsd.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/lsd.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cgan.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cgan.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cgan.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cgan.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cgan.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/cgan.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/matrix.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/matrix.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/matrix.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/matrix.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/matrix.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/matrix.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/network.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/network.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/network.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/network.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/network.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/network.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/nightmare.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/nightmare.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/nightmare.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/nightmare.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/nightmare.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/nightmare.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/normalization_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/normalization_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/normalization_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/normalization_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/normalization_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/normalization_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/option_list.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/option_list.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/option_list.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/option_list.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/option_list.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/option_list.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/parser.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/parser.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/parser.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/parser.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/parser.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/parser.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/region_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/region_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/region_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/region_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/region_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/region_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/regressor.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/regressor.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/regressor.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/regressor.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/regressor.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/regressor.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/reorg_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/reorg_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/reorg_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/reorg_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/reorg_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/reorg_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/rnn_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/rnn_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/rnn_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/rnn_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/rnn_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/rnn_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn_vid.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn_vid.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn_vid.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn_vid.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn_vid.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/rnn_vid.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/route_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/route_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/route_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/route_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/route_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/route_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/shortcut_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/shortcut_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/shortcut_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/shortcut_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/shortcut_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/shortcut_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/softmax_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/softmax_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/softmax_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/softmax_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/softmax_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/softmax_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/segmenter.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/segmenter.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/segmenter.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/segmenter.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/segmenter.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/segmenter.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/super.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/super.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/super.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/super.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/super.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/super.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/swag.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/swag.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/swag.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/swag.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/swag.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/swag.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/tag.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/tag.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/tag.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/tag.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/tag.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/tag.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/tree.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/tree.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/tree.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/tree.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/tree.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/tree.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/utils.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/utils.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/utils.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/utils.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/utils.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/utils.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/voxel.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/voxel.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/voxel.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/voxel.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/voxel.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/voxel.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/writing.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/writing.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/writing.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/writing.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/writing.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/writing.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/yolo.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/yolo.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/yolo.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/yolo.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/yolo.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/yolo.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo4_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo4_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo4_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo4_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo4_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/yolo4_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gaussian_yolo4_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gaussian_yolo4_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gaussian_yolo4_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gaussian_yolo4_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gaussian_yolo4_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/gaussian_yolo4_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/upsample_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/upsample_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/upsample_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/upsample_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/upsample_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/upsample_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/logistic_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/logistic_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/logistic_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/logistic_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/logistic_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/logistic_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/l2norm_layer.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/l2norm_layer.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/l2norm_layer.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/l2norm_layer.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/l2norm_layer.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/l2norm_layer.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activation_kernels.c.o:(.bss+0x18): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activation_kernels.c.o:(.bss+0x20): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activation_kernels.c.o:(.bss+0x28): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activation_kernels.c.o:(.bss+0x30): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activation_kernels.c.o:(.bss+0x38): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/activation_kernels.c.o:(.bss+0x40): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer_kernels.c.o:(.bss+0x18): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer_kernels.c.o:(.bss+0x20): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer_kernels.c.o:(.bss+0x28): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer_kernels.c.o:(.bss+0x30): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer_kernels.c.o:(.bss+0x38): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/avgpool_layer_kernels.c.o:(.bss+0x40): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas_kernels.c.o:(.bss+0x1a0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas_kernels.c.o:(.bss+0x1a8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas_kernels.c.o:(.bss+0x1b0): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas_kernels.c.o:(.bss+0x1b8): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas_kernels.c.o:(.bss+0x1c0): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/blas_kernels.c.o:(.bss+0x1c8): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/col2im_kernels.c.o:(.bss+0x10): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/col2im_kernels.c.o:(.bss+0x18): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/col2im_kernels.c.o:(.bss+0x20): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/col2im_kernels.c.o:(.bss+0x28): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/col2im_kernels.c.o:(.bss+0x30): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/col2im_kernels.c.o:(.bss+0x38): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_kernels.c.o:(.bss+0x28): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_kernels.c.o:(.bss+0x30): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_kernels.c.o:(.bss+0x38): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_kernels.c.o:(.bss+0x40): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_kernels.c.o:(.bss+0x48): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/convolutional_kernels.c.o:(.bss+0x50): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer_kernels.c.o:(.bss+0x18): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer_kernels.c.o:(.bss+0x20): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer_kernels.c.o:(.bss+0x28): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer_kernels.c.o:(.bss+0x30): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer_kernels.c.o:(.bss+0x38): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/crop_layer_kernels.c.o:(.bss+0x40): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_kernels.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_kernels.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_kernels.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_kernels.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_kernels.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/deconvolutional_kernels.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer_kernels.c.o:(.bss+0x10): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer_kernels.c.o:(.bss+0x18): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer_kernels.c.o:(.bss+0x20): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer_kernels.c.o:(.bss+0x28): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer_kernels.c.o:(.bss+0x30): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/dropout_layer_kernels.c.o:(.bss+0x38): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col_kernels.c.o:(.bss+0x10): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col_kernels.c.o:(.bss+0x18): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col_kernels.c.o:(.bss+0x20): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col_kernels.c.o:(.bss+0x28): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col_kernels.c.o:(.bss+0x30): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/im2col_kernels.c.o:(.bss+0x38): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer_kernels.c.o:(.bss+0x18): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer_kernels.c.o:(.bss+0x20): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer_kernels.c.o:(.bss+0x28): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer_kernels.c.o:(.bss+0x30): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer_kernels.c.o:(.bss+0x38): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/maxpool_layer_kernels.c.o:(.bss+0x40): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/opencl.c.o:(.bss+0x28): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/opencl.c.o:(.bss+0x18): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/opencl.c.o:(.bss+0x40): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/opencl.c.o:(.bss+0x38): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/opencl.c.o:(.bss+0x30): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/opencl.c.o:(.bss+0x20): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image_opencv.cpp.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image_opencv.cpp.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image_opencv.cpp.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image_opencv.cpp.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image_opencv.cpp.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/src/image_opencv.cpp.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/darknet.c.o:(.bss+0x0): multiple definition of `opencl_devices'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x0): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/darknet.c.o:(.bss+0x8): multiple definition of `opencl_queues'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x8): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/darknet.c.o:(.bss+0x10): multiple definition of `opencl_context'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x10): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/darknet.c.o:(.bss+0x18): multiple definition of `cl_native_address_bits_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x18): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/darknet.c.o:(.bss+0x20): multiple definition of `cl_native_max_group_size_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x20): first defined here
/usr/bin/ld: CMakeFiles/bindarknet.dir/examples/darknet.c.o:(.bss+0x28): multiple definition of `cl_native_double_width_s'; CMakeFiles/bindarknet.dir/src/activation_layer.c.o:(.bss+0x28): first defined here
collect2: error: ld returned 1 exit status
make[2]: *** [CMakeFiles/bindarknet.dir/build.make:1467: darknet] Error 1
make[1]: *** [CMakeFiles/Makefile2:87: CMakeFiles/bindarknet.dir/all] Error 2
make: *** [Makefile:136: all] Error 2

OS: Arch Linux with opencl-amd installed
i'm getting this error while compiling. am i going wrong somewhere or is it an issue on your side?
btw, i ran mkdir build; cd build; cmake ..; make

gemm_gpu: clblasSgemm failed. Errorcode: -1024

I'm getting this issue several times while training, not sure why.

cv::Exception matrix_wrap.cpp:771: error: (-215:Assertion failed) (flags & FIXED_TYPE) != 0 in function 'type'

The error can be reproduced by following the setup commands in a fresh and clean installation of Ubuntu 20.04.1 LTS.

After compiling and building everything, nothing seems wrong at all... until you try to use darknet:

user@user-pc:~/github/darknet$ ./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
Device IDs: 1
Device ID: 0
Device name: Ellesmere
Device vendor: Advanced Micro Devices, Inc.
Device opencl availability: OpenCL 1.2 AMD-APP (3180.7)
Device opencl used: 3180.7
Device double precision: YES
Device max group size: 256
Device address bits: 64
layer     filters    size              input                output
    0 conv     32  3 x 3 / 1   608 x 608 x   3   ->   608 x 608 x  32  0.639 BFLOPs
    1 conv     64  3 x 3 / 2   608 x 608 x  32   ->   304 x 304 x  64  3.407 BFLOPs
   [...]
  105 conv    255  1 x 1 / 1    76 x  76 x 256   ->    76 x  76 x 255  0.754 BFLOPs
  106 yolo
Loading weights from yolov3.weights...Done!
data/dog.jpg: Predicted in 1.640484 seconds.
terminate called after throwing an instance of 'cv::Exception'
  what():  OpenCV(3.4.12) /home/user/opencv-3.4.12/modules/core/src/matrix_wrap.cpp:771: error: (-215:Assertion failed) (flags & FIXED_TYPE) != 0 in function 'type'

Aborted (core dumped)
user@user-pc:~/github/darknet$

I already tried downgrading opencv to 3.4.0 as @AlexeyAB proposed for his repo in an issue:

This is a bug in OpenCV 3.4.1 C API
Use OpenCV 3.4.0

Also found this similar issue:

I can see you are using OpenCV 3.4.1, there is currently a bug in C API
Use OpenCV 3.4.0 or lower

but it threw another error (which had something to do with an unimplemented method of a cvWindow or something like that).

I don't know a thing about the OpenCV API, however, your project seems to be using the good C++ API and not the C deprecated one (read from here), so I just don't get what its wrong...

Aborted when run 2 training from libdarknet.so at the same time

Hello, I compiled darknet and libdarknet.so on my macbook pro.
It is fine when I ran "darknet detector train" on the same GPU at the same.
But when turn to libdarknet.so,
the second training will be very slow and finally aborted with no more log info.

I load libdarknet.so in the both python code and C,
and the behaviors are same that training a detector on the one GPU is safe,
or two trainings on the different GPU respectively is also safe,
two training on the one GPU is aborted(in the most case one of the trainings aborted, sometimes both).

Wish your help, thank you.

How to build on Windows10?

I success used Cmake to make a .sln file.
And I'm trying to compile it by Visual Studio 2019.
But it has too much error, after I fix one more error come out.
Could anyone help me build it on windwos?

Please kindly help us about Not convergent network

Hi sowson,

We used your darknet network which running in our Macbook Pro Opencl, but so weird about our training based on your code, and it seems to be Obj: 0.500000, No Obj: 0.500000 all the time for hundreds circle training. And training is not convergent all the time.
Our data is from https://timebutt.github.io/static/how-to-train-yolov2-to-detect-custom-objects/ this article dataset.
network as below:

my yolov2.cfg as below:
[net]

Testing

#batch=1
#subdivisions=1

Training

batch=32
subdivisions=4
height=416
width=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 80200
policy=steps
steps=40000,60000
scales=.1,.1
.....
.....
[convolutional]
size=1
stride=1
pad=1
filters=30
activation=linear

[region]
#anchors = 1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071
#anchors = 5,11, 9,19, 51,62, 104,114, 181,209, 279,376, 400,289, 357,377, 390,388
anchors = 6,14, 70,82, 176,190, 291,375, 382,377
bias_match=1
classes=1
coords=4
num=5
softmax=1
jitter=.3
rescore=1
....

Please kindly help about our issues, thanks.

Error while running darknet binary

Hello,
I have just run into the problem when tried to use your code:

./darknet detect cfg/yolov2.cfg yolov2.weights ./snapshot.jpg -thresh 0.2

Device IDs: 1
Device ID: 0
Device name: Oland
Device vendor: Advanced Micro Devices, Inc.
Device opencl availability: OpenCL 1.2 AMD-APP (3004.6)
Device opencl used: 3004.6
Device double precision: YES
Device max group size: 256
Device address bits: 64
opencl_load: could not compile. error: CL_COMPILE_PROGRAM_FAILURE
CL_PROGRAM_BUILD_LOG:
"/tmp/OCL6829T3.cl", line 1: error: function "atom_cmpxchg" declared implicitly

__kernel void test_kernel(int N, __global float *input, __global float *output, __global float *expected) { int index = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; output[index] = sqrt(input[index]); index += 1; input[index] = output[index-1]; output[index] = log(input[index]); index += 1; input[index] = output[index-1]; output[index] = pow(input[index], output[index-2]); index += 1; input[index] = output[index-1]; output[index] = -exp(input[index]); index += 1; input[index] = output[index-1]; output[index] = fabs(input[index]); index += 1; input[index] = output[index-1]; output[index] = sin(input[index]); index += 1; input[index] = output[index-1]; output[index] = cos(input[index]); } static void atomicAdd(volatile __global float *a, float v) { union { float f; unsigned int i; } o; o.i = 0; union { float f; unsigned int i; } n; n.i = 1; do { o.f = *a; n.f = o.f + v; } while (atom_cmpxchg((__global unsigned int *)a, o.i, n.i) != o.i); } __kernel void scale_bias_kernel(int N, __global float *output, __global float *biases, int batch, int n, int size) { int index = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int i = (index % (nsize) / size); output[index] *= biases[i]; } __kernel void backward_scale_kernel(int N, int batch, int n, int size, __global float *x_norm, __global float *delta, __global float *scale_updates) { int index = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int i = (index % (nsize) / size); scale_updates[i] += delta[index]*x_norm[index]; } __kernel void add_bias_kernel(int N, __global float *output, __global float *biases, int batch, int n, int size) { int index = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int i = (index % (nsize) / size); output[index] += biases[i]; } __kernel void backward_bias_kernel(int N, int batch, int n, int size, __global float *bias_updates, __global float *delta) { int index = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int i = (index % (nsize) / size); bias_updates[i] += delta[index]; } __kernel void mean_kernel(int N, __global float *x, int batch, int filters, int spatial, __global float *mean) { float scale = 1.f/(batch * spatial); int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; mean[i] = 0; int j, k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; mean[i] += x[index]; } } mean[i] *= scale; } __kernel void variance_kernel(int N, __global float *x, __global float *mean, int batch, int filters, int spatial, __global float *variance) { float scale = 1.f/(batch * spatial - 1); int id = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; variance[i] = 0; int j,k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; variance[i] += pow((x[index] - mean[i]), 2); } } variance[i] *= scale; } __kernel void mean_delta_kernel(int N, __global float *delta, __global float *variance, int batch, int filters, int spatial, __global float *mean_delta) { int id = (get_group_id(0) + get_group_id(1) * get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; mean_delta[i] = 0; int j, k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; mean_delta[i] += delta[index]; } } mean_delta[i] *= (-1.f/sqrt(variance[i] + .00001f)); } __kernel void variance_delta_kernel(int N, __global float *x, __global float *delta, __global float *mean, __global float *variance, int batch, int filters, int spatial, __global float *variance_delta) { int id = (get_group_id(0) + get_group_id(1) * get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int i = id; variance_delta[i] = 0; int j,k; for (j = 0; j < batch; ++j) { for (k = 0; k < spatial; ++k) { int index = j * filters * spatial + i * spatial + k; variance_delta[i] += delta[index] * (x[index] - mean[i]); } } variance_delta[i] *= -.5f * pow(variance[i] + .00001f, (float)(-3.f/2.f)); } __kernel void accumulate_kernel(__global float *x, int n, int groups, __global float *sum) { int k; int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (i >= groups) return; sum[i] = 0; for(k = 0; k < n; ++k){ sum[i] += x[kgroups + i]; } } __kernel void fast_mean_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *x, __global float *mean) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j, k, s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += x[index]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { mean[i] = 0; for (s = 0; s < tuning; ++s) { mean[i] += sums[s]; } mean[i] /= (spatial * batch); } } __kernel void fast_variance_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *x, __global float *mean, __global float *variance) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j,k,s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += pow((x[index] - mean[i]), 2); } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { variance[i] = 0; for (s = 0; s < tuning; ++s) { variance[i] += sums[s]; } variance[i] /= (spatial * batch - 1); } } __kernel void fast_mean_delta_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *variance, __global float *delta, __global float *mean_delta) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j,k,s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += delta[index]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { mean_delta[i] = 0; for (s = 0; s < tuning; ++s) { mean_delta[i] += sums[s]; } mean_delta[i] *= (-1.f/sqrt(variance[i] + .00001f)); } } __kernel void fast_variance_delta_kernel(int tuning, __local float *sums, int filters, int batch, int spatial, __global float *x, __global float variance, __global float delta, __global float mean, __global float variance_delta) { int t = get_global_id(0); if (t >= tuning) return; int i = get_global_id(1); if (i >= filters) return; sums[t] = 0; int j,k,s; for (j = 0; j < batch; ++j) { for (k = t; k < spatial; k += tuning) { int index = j * filters * spatial + i * spatial + k; sums[t] += delta[index] * (x[index] - mean[i]); } } barrier(CLK_GLOBAL_MEM_FENCE); if (t == tuning-1) { variance_delta[i] = 0; for (s = 0; s < tuning; ++s) { variance_delta[i] += sums[s]; } variance_delta[i] = -.5f * pow(variance[i] + .00001f, (float)(-3.f/2.f)); } } __kernel void adam_kernel(int N, __global float x, __global float m, __global float v, float B1, float B2, float rate, float eps, int t) { int index = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; x[index] = x[index] + (rate * sqrt(1.f-pow(B2, t)) / (1.f-pow(B1, t)) * m[index] / (sqrt((v[index] + eps)))); } __kernel void normalize_kernel(int N, __global float x, __global float mean, __global float variance, int batch, int filters, int spatial) { int id = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int b = (id / (filtersspatial)); int f = (id % (filtersspatial) / spatial); int i = (id % spatial); int index = bfiltersspatial + fspatial + i; x[index] = (x[index] - mean[f])/(sqrt(variance[f] + .00001f)); } __kernel void normalize_delta_kernel(int N, __global float x, __global float mean, __global float variance, __global float mean_delta, __global float variance_delta, int batch, int filters, int spatial, __global float delta) { int id = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= N) return; int j = (id / (filtersspatial)); int f = (id % (filtersspatial) / spatial); int k = (id % spatial); int index = jfiltersspatial + fspatial + k; delta[index] = delta[index] * 1.f/(sqrt(variance[f] + .00001f)) + variance_delta[f] * 2. * (x[index] - mean[f]) / (spatial * batch) + mean_delta[f]/(spatialbatch); } __kernel void l2norm_kernel(int N, __global float x, __global float dx, int batch, int filters, int spatial) { int index = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (index >= N) return; int b = index / spatial; int i = index % spatial; int f; float sum = 0; for(f = 0; f < filters; ++f){ int index = bfiltersspatial + fspatial + i; sum += pow(x[index], 2.f); } sum = sqrt(sum); if(sum == 0) sum = 1.f; for(f = 0; f < filters; ++f){ int index = bfiltersspatial + fspatial + i; x[index] /= sum; dx[index] = (1 - x[index]) / sum; } } __kernel void reorg_kernel(int N, __global float x, int w, int h, int c, int batch, int stride, int forward, __global float out) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i >= N) return; int in_index = i; int in_w = i%w; i = i/w; int in_h = i%h; i = i/h; int in_c = i%c; i = i/c; int b = i%batch; int out_c = c/(stridestride); int c2 = in_c % out_c; int offset = in_c / out_c; int w2 = in_wstride + offset % stride; int h2 = in_hstride + offset / stride; int out_index = w2 + wstride(h2 + hstride(c2 + out_cb)); if(forward) out[out_index] = x[in_index]; else out[in_index] = x[out_index]; } __kernel void axpy_kernel(int N, __const float ALPHA, __global float X, int OFFX, int INCX, __global float Y, int OFFY, int INCY) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[iINCY+OFFY] += ALPHAX[iINCX+OFFX]; } __kernel void pow_kernel(int N, __const float ALPHA, __global float X, int OFFX, int INCX, __global float Y, int OFFY, int INCY) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[iINCY + OFFY] = pow(X[iINCX + OFFX], ALPHA); } __kernel void const_kernel(int N, __const float ALPHA, __global float X, int OFFX, int INCX) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[iINCX + OFFX] = ALPHA; } __kernel void constrain_kernel(int N, __const float ALPHA, __global float X, int INCX) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[iINCX] = min(ALPHA, max(-ALPHA, X[iINCX])); } __kernel void supp_kernel(int N, __const float ALPHA, __global float X, int INCX) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) { if((X[iINCX] * X[iINCX]) < (ALPHA * ALPHA)) X[iINCX] = 0; } } __kernel void add_kernel(int N, __const float ALPHA, __global float X, int INCX) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[iINCX] += ALPHA; } __kernel void scal_kernel(int N, __const float ALPHA, __global float X, int INCX) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[iINCX] = ALPHA; } __kernel void fill_kernel(int N, __const float ALPHA, __global float X, int OFFX, int INCX) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) X[iINCX + OFFX] = ALPHA; } __kernel void mask_kernel(int n, __global float x, float mask_num, __global float mask, float val) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n && mask[i] == mask_num) x[i] = val; } __kernel void copy_kernel(int N, __global float X, int OFFX, int INCX, __global float Y, int OFFY, int INCY) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[iINCY + OFFY] = X[iINCX + OFFX]; } __kernel void mul_kernel(int N, __global float X, int INCX, __global float Y, int INCY) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < N) Y[iINCY] = X[iINCX]; } __kernel void flatten_kernel(int N, __global float x, int spatial, int layers, int batch, int forward, __global float out) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i >= N) return; int in_s = i%spatial; i = i/spatial; int in_c = i%layers; i = i/layers; int b = i; int i1 = blayersspatial + in_cspatial + in_s; int i2 = blayersspatial + in_slayers + in_c; if (forward) out[i2] = x[i1]; else out[i1] = x[i2]; } __kernel void shortcut_kernel(int size, int minw, int minh, int minc, int stride, int sample, int batch, int w1, int h1, int c1, __global float add, int w2, int h2, int c2, float s1, float s2, __global float out) { int id = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= size) return; int i = id % minw; id /= minw; int j = id % minh; id /= minh; int k = id % minc; id /= minc; int b = id % batch; int out_index = isample + w2(jsample + h2(k + c2b)); int add_index = istride + w1(jstride + h1(k + c1b)); out[out_index] = s1out[out_index] + s2add[add_index]; } __kernel void smooth_l1_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float diff = truth[i] - pred[i]; float abs_val = fabs(diff); if(abs_val < 1) { error[i] = diff * diff; delta[i] = diff; } else { error[i] = 2abs_val - 1; delta[i] = (diff > 0) ? 1 : -1; } } } __kernel void softmax_x_ent_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n) { float t = truth[i]; float p = pred[i]; error[i] = (t!=0) ? -log(p) : 0; delta[i] = t-p; } } __kernel void logistic_x_ent_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float t = truth[i]; float p = pred[i]; error[i] = -tlog(p+.0000001f) - (1.f-t)*log(1.f-p+.0000001f); delta[i] = t-p; } } __kernel void l2_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float t = truth[i]; float p = pred[i]; float diff = t-p; error[i] = pow(diff,2); delta[i] = diff; } } __kernel void l1_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ float diff = truth[i] - pred[i]; error[i] = fabs(diff); delta[i] = (diff > 0) ? 1 : -1; } } __kernel void wgan_kernel(int n, __global float *pred, __global float *truth, __global float *delta, __global float *error) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ error[i] = (truth[i]!=0) ? -pred[i] : pred[i]; delta[i] = (truth[i] > 0) ? 1 : -1; } } __kernel void weighted_sum_kernel(int n, __global float *a, __global float *b, __global float *s, __global float *c) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ c[i] = s[i]a[i] + (1-s[i])(b ? b[i] : 0); } } __kernel void weighted_delta_kernel(int n, __global float *a, __global float *b, __global float *s, __global float *da, __global float *db, __global float *ds, __global float *dc) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ if(da) da[i] += dc[i] * s[i]; db[i] += dc[i] * (1-s[i]); ds[i] += dc[i] * a[i] + dc[i] * -b[i]; } } __kernel void mult_add_into_kernel(int n, __global float *a, __global float *b, __global float *c) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n){ c[i] += a[i]*b[i]; } } __kernel void deinter_kernel(int NX, __global float *X, int NY, __global float *Y, int B, __global float OUT) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < (NX+NY)B){ int b = i / (NX+NY); int j = i % (NX+NY); if (j < NX){ if(X) X[bNX + j] += OUT[i]; } else { if(Y) Y[bNY + j - NX] += OUT[i]; } } } __kernel void inter_kernel(int NX, __global float X, int NY, __global float Y, int B, __global float OUT) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < (NX+NY)B){ int b = i / (NX+NY); int j = i % (NX+NY); if (j < NX){ OUT[i] = X[bNX + j]; } else { OUT[i] = Y[bNY + j - NX]; } } } __kernel void softmax_device(__global float input, int n, float temp, int stride, __global float output) { int i; float sum = 0; float largest = -FLT_MAX; for(i = 0; i < n; ++i){ int val = input[istride]; largest = (val>largest) ? val : largest; } for(i = 0; i < n; ++i){ float e = exp(input[istride]/temp - largest/temp); sum += e; output[istride] = e; } for(i = 0; i < n; ++i){ output[istride] /= sum; } } __kernel void softmax_kernel(__global float input, int offset, int n, int batch, int batch_offset, int groups, int group_offset, int stride, float temp, __global float output) { int id = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= batchgroups) return; int b = id / groups; int g = id % groups; softmax_device(input + bbatch_offset + ggroup_offset + offset, n, temp, stride, output + bbatch_offset + ggroup_offset + offset); } __kernel void softmax_tree_kernel(__global float *input, int offset, int index, int spatial, int batch, int stride, float temp, __global float *output, int groups, __global float group_size, __global float group_offset) { int id = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if (id >= spatialbatchgroups) return; int s = id % spatial; id = id / spatial; int g = id % groups; int b = id / groups; int goff = group_offset[g]spatial; int boff = bstride; softmax_device(input + offset + goff + boff + s, group_size[g], temp, spatial, output + offset + goff + boff + s); } __kernel void scale_mask_kernel(int n, __global float x, float mask_num, __global float mask, float scale) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n && mask[i] == mask_num) x[i] = scale; } __kernel void dot_kernel(__global float output, float scale, int batch, int n, int size, __global float delta) { int index = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); int f1 = index / n; int f2 = index % n; if (f2 <= f1) return; float sum = 0; float norm1 = 0; float norm2 = 0; int b, i; for(b = 0; b < batch; ++b){ for(i = 0; i < size; ++i){ int i1 = b * size * n + f1 * size + i; int i2 = b * size * n + f2 * size + i; sum += output[i1] * output[i2]; norm1 += output[i1] * output[i1]; norm2 += output[i2] * output[i2]; } } norm1 = sqrt(fabs(norm1)); norm2 = sqrt(fabs(norm2)); float norm = norm1 * norm2; sum = sum / norm; for(b = 0; b < batch; ++b){ for(i = 0; i < size; ++i){ int i1 = b * size * n + f1 * size + i; int i2 = b * size * n + f2 * size + i; delta[i1] += - scale * sum * output[i2] / norm; delta[i2] += - scale * sum * output[i1] / norm; } } } __kernel void upsample_kernel(int N, __global float x, int w, int h, int c, int batch, int stride, int forward, float scale, __global float out) { int i = (get_group_id(0) + get_group_id(1)get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i >= N) return; int out_index = i; int out_w = i%(wstride); i = i/(wstride); int out_h = i%(hstride); i = i/(hstride); int out_c = i%c; i = i/c; int b = i%batch; int in_w = out_w / stride; int in_h = out_h / stride; int in_c = out_c; int in_index = bwhc + in_cwh + in_hw + in_w; if(forward) out[out_index] += scale * x[in_index]; else atomicAdd(&x[in_index], scale * out[out_index]); } __kernel void gemm_kernel( int tuning, __local float sums, int TA, int TB, int M, int N, int K, __const float ALPHA, __global float *A, int offset_A, int lda, __global float *B, int offset_B, int ldb, __const float BETA, __global float C, int offset_C, int ldc) { int td = get_global_id(0); if (td > tuning) return; int id = get_global_id(1); if (id > NM) return; int iM = id / N; int jN = id % N; int kK = 0; int ts = 0; C[iM * ldc + jN + offset_C] *= BETA; sums[td] = 0; for(kK = td; kK < K; kK += tuning) { if (TA==0 && TB==0) { sums[td] += ALPHA * A[iM * lda + kK + offset_A] * B[kK * ldb + jN + offset_B]; } else if (TA==1 && TB==0) { sums[td] += ALPHA * A[kK * lda + iM + offset_A] * B[kK * ldb + jN + offset_B]; } else if (TA==0 && TB==1) { sums[td] += ALPHA * A[iM * lda + kK + offset_A] * B[jN * ldb + kK + offset_B]; } else { sums[td] += ALPHA * A[iM + kK * lda + offset_A] * B[kK + jN * ldb + offset_B]; } } barrier(CLK_GLOBAL_MEM_FENCE); if (td == tuning-1) { for(ts = 0; ts < tuning; ++ts) { if (TA==0 && TB==0) { C[iM * ldc + jN + offset_C] += sums[ts]; } else if (TA==1 && TB==0) { C[iM * ldc + jN + offset_C] += sums[ts]; } else if (TA==0 && TB==1) { C[iM * ldc + jN + offset_C] += sums[ts]; } else { C[iM * ldc + jN + offset_C] += sums[ts]; } } } }
^

1 error detected in the compilation of "/tmp/OCL6829T3.cl".
Frontend phase failed compilation.

Avg loss straight to zero

Hi, thanks for doing this opencl fork. I've got further on getting things working for my RX 580 than others.

I needed to do sudo ldconfig to get it to run, and then needed to put:

*output = clLinkProgram(opencl_contexts[opencl_device_id_t], opencl_device_ct_t, opencl_devices, "", 1, prog, NULL, NULL, &clErr);

in opencl.c

I'm now to train on the voc data set, following AlexeyAB's tutorial. The problem is, the average loss function is going straight to zero.

Here is the output from the first iterations, thanks:

Loading weights from darknet53.conv.74...Done!
Learning Rate: 0.001, Momentum: 0.9, Decay: 0.0005
Resizing
448
Loaded: 0.000054 seconds
Region 82 Avg IOU: 0.145264, Class: 0.557355, Obj: 0.292876, No Obj: 0.494451, .5R: 0.000000, .75R: 0.000000, count: 9
Region 94 Avg IOU: 0.149600, Class: 0.676368, Obj: 0.355952, No Obj: 0.513023, .5R: 0.142857, .75R: 0.000000, count: 14
Region 106 Avg IOU: 0.007626, Class: 0.401388, Obj: 0.633496, No Obj: 0.471143, .5R: 0.000000, .75R: 0.000000, count: 1
Region 82 Avg IOU: 0.257950, Class: 0.426642, Obj: 0.322373, No Obj: 0.493180, .5R: 0.200000, .75R: 0.000000, count: 10
Region 94 Avg IOU: 0.137465, Class: 0.400465, Obj: 0.394822, No Obj: 0.512317, .5R: 0.000000, .75R: 0.000000, count: 7
Region 106 Avg IOU: 0.202138, Class: 0.586369, Obj: 0.364813, No Obj: 0.473299, .5R: 0.250000, .75R: 0.000000, count: 4
Region 82 Avg IOU: 0.291640, Class: 0.488285, Obj: 0.518656, No Obj: 0.493739, .5R: 0.166667, .75R: 0.000000, count: 6
Region 94 Avg IOU: 0.093404, Class: 0.393986, Obj: 0.703347, No Obj: 0.514841, .5R: 0.000000, .75R: 0.000000, count: 9
Region 106 Avg IOU: 0.379017, Class: 0.924878, Obj: 0.687865, No Obj: 0.475272, .5R: 0.000000, .75R: 0.000000, count: 1
Region 82 Avg IOU: 0.285344, Class: 0.346855, Obj: 0.317452, No Obj: 0.492233, .5R: 0.142857, .75R: 0.000000, count: 7
Region 94 Avg IOU: 0.130376, Class: 0.506110, Obj: 0.634440, No Obj: 0.512611, .5R: 0.000000, .75R: 0.000000, count: 5
Region 106 Avg IOU: 0.119781, Class: 0.555439, Obj: 0.783421, No Obj: 0.472111, .5R: 0.000000, .75R: 0.000000, count: 2
Region 82 Avg IOU: 0.286759, Class: 0.532216, Obj: 0.521017, No Obj: 0.493246, .5R: 0.100000, .75R: 0.000000, count: 10
Region 94 Avg IOU: 0.137215, Class: 0.514404, Obj: 0.459499, No Obj: 0.513389, .5R: 0.000000, .75R: 0.000000, count: 5
Region 106 Avg IOU: 0.153096, Class: 0.403162, Obj: 0.553437, No Obj: 0.470921, .5R: 0.000000, .75R: 0.000000, count: 4
Region 82 Avg IOU: 0.223061, Class: 0.484147, Obj: 0.489988, No Obj: 0.492903, .5R: 0.117647, .75R: 0.000000, count: 17
Region 94 Avg IOU: 0.040685, Class: 0.678096, Obj: 0.464522, No Obj: 0.513007, .5R: 0.000000, .75R: 0.000000, count: 5
Region 106 Avg IOU: 0.351594, Class: 0.760295, Obj: 0.369242, No Obj: 0.469966, .5R: 0.000000, .75R: 0.000000, count: 2
Region 82 Avg IOU: 0.209237, Class: 0.635235, Obj: 0.570351, No Obj: 0.493333, .5R: 0.000000, .75R: 0.000000, count: 10
Region 94 Avg IOU: 0.220527, Class: 0.463515, Obj: 0.465429, No Obj: 0.514360, .5R: 0.000000, .75R: 0.000000, count: 5
Region 106 Avg IOU: 0.260902, Class: 0.483188, Obj: 0.516514, No Obj: 0.472673, .5R: 0.000000, .75R: 0.000000, count: 4
Region 82 Avg IOU: 0.248426, Class: 0.553127, Obj: 0.496878, No Obj: 0.492399, .5R: 0.000000, .75R: 0.000000, count: 11
Region 94 Avg IOU: 0.355078, Class: 0.793197, Obj: 0.322255, No Obj: 0.512674, .5R: 0.500000, .75R: 0.000000, count: 2
Region 106 Avg IOU: 0.063738, Class: 0.852796, Obj: 0.704434, No Obj: 0.472485, .5R: 0.000000, .75R: 0.000000, count: 1
1: 1132.090576, 1132.090576 avg, 0.000000 rate, 109.115808 seconds, 64 images

MultiGPU - Crash when training

Hi @sowson ,
I found sometimes the program will crash when training my network, but I am not sure why, Have you any idea about my issue ?

Issue when creating the file at the _make_ command

Hey, I have been running into an issue when I am creating the darknet executable file. I am on macOS Catalina. The python version is 3.7.6 . When I try to run the make -j8 command after running the cmake command, I run into the following error.

If you need any more information, I am happy to provide it.

Thanks

Bounding box incorrect with tiny YOLO v3

Hello, I ran a detection with a pretrained model with default tiny YOLO v3 . The input photo is of width 640 and length 320.
The detection was correct ie all objects were rightly detected but bounding boxes were wrong.
Can you please give me any suggestions, what can be the issue

opencl_load: could not compile. error: CL_UNKNOWN_ERROR

Hey sorry to bother you again, I´m trying to setup darknet on a Hackintosh.
The compile went great but when testing with: ./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg

But I get this error:

Device ID: 0
Device name: GeForce GTX 570
Device vendor: NVIDIA
Device opencl availability: OpenCL 1.1 
Device opencl used: 10.4.3 310.41.35f01
Device double precision: YES
Device max group size: 1024
Device address bits: 32
opencl_load: could not compile. error: CL_UNKNOWN_ERROR
CL_PROGRAM_BUILD_LOG:
error: macro definitions used to build the precompiled header are missing
<built-in>:141:1: note: using this macro definition from precompiled header
#define cl_khr_fp64 1
^

CODE:
float lhtan_activate_kernel(float x); float lhtan_gradient_kernel(float x); float hardtan_activate_kernel(float x); float linear_activate_kernel(float x); float logistic_activate_kernel(float x); float loggy_activate_kernel(float x); float relu_activate_kernel(float x); float elu_activate_kernel(float x); float selu_activate_kernel(float x); float relie_activate_kernel(float x); float ramp_activate_kernel(float x); float leaky_activate_kernel(float x); float tanh_activate_kernel(float x); float plse_activate_kernel(float x); float stair_activate_kernel(float x); float hardtan_gradient_kernel(float x); float linear_gradient_kernel(float x); float logistic_gradient_kernel(float x); float loggy_gradient_kernel(float x); float relu_gradient_kernel(float x); float elu_gradient_kernel(float x); float selu_gradient_kernel(float x); float relie_gradient_kernel(float x); float ramp_gradient_kernel(float x); float leaky_gradient_kernel(float x); float tanh_gradient_kernel(float x); float plse_gradient_kernel(float x); float stair_gradient_kernel(float x); typedef enum{ LOGISTIC, RELU, RELIE, LINEAR, RAMP, TANH, PLSE, LEAKY, ELU, LOGGY, STAIR, HARDTAN, LHTAN, SELU } ACTIVATION; float activate_kernel(float x, ACTIVATION a); float gradient_kernel(float x, ACTIVATION a); float lhtan_activate_kernel(float x) { if(x < 0) return .001f*x; if(x > 1) return .001f*(x-1.f) + 1.f; return x; } float lhtan_gradient_kernel(float x) { if(x > 0 && x < 1) return 1; return .001; } float hardtan_activate_kernel(float x) { if (x < -1) return -1; if (x > 1) return 1; return x; } float linear_activate_kernel(float x){return x;} float logistic_activate_kernel(float x){return 1.f/(1.f + exp(-x));} float loggy_activate_kernel(float x){return 2.f/(1.f + exp(-x)) - 1;} float relu_activate_kernel(float x){return x*(x>0);} float elu_activate_kernel(float x){return (x >= 0)*x + (x < 0)*(exp(x)-1);} float selu_activate_kernel(float x){return (x >= 0)*1.0507f*x + (x < 0)*1.0507f*1.6732f*(exp(x)-1);} float relie_activate_kernel(float x){return (x>0) ? x : .01f*x;} float ramp_activate_kernel(float x){return x*(x>0)+.1f*x;} float leaky_activate_kernel(float x){return (x>0) ? x : .1f*x;} float tanh_activate_kernel(float x){return (2.f/(1 + exp(-2*x)) - 1);} float plse_activate_kernel(float x) { if(x < -4) return .01f * (x + 4); if(x > 4) return .01f * (x - 4) + 1; return .125f*x + .5f; } float stair_activate_kernel(float x) { int n = floor(x); if (n%2 == 0) return floor(x/2); else return (x - n) + floor(x/2); } float hardtan_gradient_kernel(float x) { if (x > -1 && x < 1) return 1; return 0; } float linear_gradient_kernel(float x){return 1;} float logistic_gradient_kernel(float x){return (1-x)*x;} float loggy_gradient_kernel(float x) { float y = (x+1)/2; return 2*(1-y)*y; } float relu_gradient_kernel(float x){return (x>0);} float elu_gradient_kernel(float x){return (x >= 0) + (x < 0)*(x + 1);} float selu_gradient_kernel(float x){return (x >= 0)*1.0507 + (x < 0)*(x + 1.0507*1.6732);} float relie_gradient_kernel(float x){return (x>0) ? 1 : .01f;} float ramp_gradient_kernel(float x){return (x>0)+.1f;} float leaky_gradient_kernel(float x){return (x>0) ? 1 : .1f;} float tanh_gradient_kernel(float x){return 1-x*x;} float plse_gradient_kernel(float x){return (x < 0 || x > 1) ? .01f : .125f;} float stair_gradient_kernel(float x) { if (floor(x) == x) return 0; return 1; } float activate_kernel(float x, ACTIVATION a) { switch(a){ case LINEAR: return linear_activate_kernel(x); case LOGISTIC: return logistic_activate_kernel(x); case LOGGY: return loggy_activate_kernel(x); case RELU: return relu_activate_kernel(x); case ELU: return elu_activate_kernel(x); case SELU: return selu_activate_kernel(x); case RELIE: return relie_activate_kernel(x); case RAMP: return ramp_activate_kernel(x); case LEAKY: return leaky_activate_kernel(x); case TANH: return tanh_activate_kernel(x); case PLSE: return plse_activate_kernel(x); case STAIR: return stair_activate_kernel(x); case HARDTAN: return hardtan_activate_kernel(x); case LHTAN: return lhtan_activate_kernel(x); } return 0; } float gradient_kernel(float x, ACTIVATION a) { switch(a){ case LINEAR: return linear_gradient_kernel(x); case LOGISTIC: return logistic_gradient_kernel(x); case LOGGY: return loggy_gradient_kernel(x); case RELU: return relu_gradient_kernel(x); case ELU: return elu_gradient_kernel(x); case SELU: return selu_gradient_kernel(x); case RELIE: return relie_gradient_kernel(x); case RAMP: return ramp_gradient_kernel(x); case LEAKY: return leaky_gradient_kernel(x); case TANH: return tanh_gradient_kernel(x); case PLSE: return plse_gradient_kernel(x); case STAIR: return stair_gradient_kernel(x); case HARDTAN: return hardtan_gradient_kernel(x); case LHTAN: return lhtan_gradient_kernel(x); } return 0; } __kernel void activate_array_kernel(__global float *x, int offset, int n, ACTIVATION a) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n) x[i + offset] = activate_kernel(x[i + offset], a); } __kernel void gradient_array_kernel(__global float *x, int offset, int n, ACTIVATION a, __global float *delta) { int i = (get_group_id(0) + get_group_id(1)*get_num_groups(0)) * get_local_size(0) + get_local_id(0); if(i < n) delta[i + offset] *= gradient_kernel(x[i + offset], a); }

sowson / darknet Goto Github PK

darknet's Introduction

THE LAST COMMIT, ALL THE BEST FOR YOU!

Project Status: Freeze!

Build on macOS or Ubuntu 20.04

Build on Windows 10 or 11 x64

Take a look 4 x GPUs on macOS (click to see video)

CLBlast instead of clBLAS for GEMM

Darknet-vNext (Improved CUDA DarkNet)

OpenCV 4

YOLO4 on OpenCL

YOLO1, YOLO2, YOLO3 on OpenCL

darknet's People

Contributors

Stargazers

Watchers

Forkers

darknet's Issues

Testing

Training

Recommend Projects

Recommend Topics

Recommend Org