Comments (11)
Hi! @wutianyiRosun
There are two questions I want to ask:
-
I test your model with 1024 * 2048 as input images. However I only got 9.5 fps on single 1080TI.
I use the code like the following
start = time.time()
out = model(img)
torch.cuda.synchronize()
print('Speed: {} fps.'.format(1.0/(time.time()-start))) -
In your paper, ICnet only 16 fps which is not consistent with his paper. (30 fps)
I don't know why. The gap between K80 and 1080TI is such large ??
Is my testing method wrong? I want to know the way you evalute your model for speed.
Also, I use my test method to test ESP-net which result in nearly the same as your paper report(49 fps)
from cgnet.
I got the same result as you, a single 1080Ti got about 9 FPS. @lxtGH
And if I didn't use torch.cuda.synchronize()
The FPS will increase to ~70Fps, this code is necessary.
from cgnet.
@Reagan1311 Yes, GPU and CPU must synchronize (CPU must wait until the end of GPU forwarding )
from cgnet.
10FPS only! I test it on 1080Ti.
I suggest that you change your arxiv paper.
from cgnet.
Hi , @wutianyiRosun
Did you use this line ?
torch.cuda.synchronize() for speed test?
from cgnet.
I met the same question. I hope I can get an answer. Thank you.
from cgnet.
I think it is wrong speed testing.
from cgnet.
Hi, @lxtGH
A1: The speed we report is the average speed on the verification set. What is your cuda and cudnn version?
A2: The speed of ICNet is tested on K80, The paper of ICNet reported 30 fps, which is tested on 1080TI. The speed between them is about two to three times the difference.
from cgnet.
@lxtGH @wutianyiRosun
I have a problem:
Pytorch DwConv's implement is not good,it's very slow. The CGNet'paper result is based on Pytorch?
from cgnet.
@wutianyiRosun If you didn't use the line of code, your speed reported in your paper is wrong.
@yyfyan What speed results you get ?
from cgnet.
@meteorshowers, @LinZhuoChen We will update in the next few days.
from cgnet.
Related Issues (20)
- CUDA run time error for the python cityscape train_code HOT 6
- What's the difference between channel-wise convolution and depth-wise convolution?
- Adding Link to Pytorch-Deeplab Repo HOT 1
- No effective change in fps even after reducing input image size while training.
- Training codes for other models?
- can i do inference using CPU HOT 1
- *gtFine_labelTrainIds.png HOT 1
- I think the codes about flops dosen't compute the AdaptiveAvgPool2d 's ops! HOT 3
- about cityscapes_inform.pkl HOT 4
- FileNotFoundError: [Errno 2] No such file or directory: './dataset/wtfile/camvid_inform.pkl' HOT 3
- GPU utilization problrm
- [ 0 1 2 4 5 6 7 8 10 11 13 255] Some problem with labels. Please check image file: ./city/gtFine/train/cologne/cologne_000000_000019_gtFine_labelTrainIds.png HOT 2
- gtFine/train/cologne/cologne_000000_000019_gtFine_labelTrainIds.png HOT 1
- No such file or directory: './dataset/wtfile/camvid_inform.pkl' HOT 1
- Camvid
- what is the format of ''cityscapes_train_list.txt''?
- TypeError: conv2d(): argument 'input' (position 1) must be Tensor, not builtin_function_or_method
- Unable to download model files from baidu's site HOT 1
- “camvid_trainval_list.txt”——What does' camvid_trainval_list. txt 'contain
- classweights HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cgnet.