Comments (10)
As I said, you should fine the best MAX_SIZE_TEST
suitable for your task (e.g., speed, resolution, etc).
I think MAX_SIZE_TEST
of 128 is too small to detect.
How about 512?
from centermask2.
Having same problem here.
from centermask2.
@youngwanLEE, I think your demo.py is broken. Having the same problem here.
from centermask2.
@Auth0rM0rgan @denverdash @Rm1n90
I fixed demo.py.
Would you like to try again?
from centermask2.
Hey @youngwanLEE, Still demo.py not working
my command line:
python demo.py --config-file ../configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml --video-input /home/xx/Downloads/avg.mp4
The error I'm getting is:
File "demo.py", line 14, in <module> from centermask.config import get_cfg ModuleNotFoundError: No module named 'centermask'
Thanks!
from centermask2.
@youngwanLEE having same error as @Auth0rM0rgan!
from centermask2.
Would you like to try again?
from centermask2.
@youngwanLEE,
Thanks, demo.py is working now.
Also, I have a question regard to Fps on 1080p video. Which one of your lite pretrained model is suitable to reach 30fps for instance segmentation on 1080P video?
I have tried all the lite pretrained models on my 1080p video but none of them could reach to 30fps. I have also tried the YOLACT 550 with ResNet50 and I was able to achieve almost ~25fps on 1080p video. according to your paper, CenterMask is faster than YOLACT but in my test yolact do the instance segmentation faster. any tips?
Thanks!
from centermask2.
While Our demo program originates from detectron2, YOLACT visualization tools are optimized well for better speed.
Inference time in many papers is usually measured using the only model forward time not including visualization step.
We also follow detectron2 rule.
I recommend you use lite models such as V-19-slim or V-19-slim-dw.
And,
if you lower the 'MAX_SIZE_TEST', you can get faster speed.
python demo/demo.py ... --opts INPUT.MAX_SIZE_TEST 512
In conclusion,
- Select well-balanced (speed and accuracy) models
- Lower
MAX_SIZE_TEST
- Search the best combination between the model and
MAX_SIZE_TEST
to the extent you accept.
from centermask2.
Hey @youngwanLEE, Thanks for the tips but when I set the INPUT.MAX_SIZE_TEST
i'm not getting any output (I mean code is working but masks are not overlay on the objects)
python demo.py --video-input /home/Downloads/tennis_720.mp4 --config-file ../configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml --opts MODEL.WEIGHTS ../centermask2-V-39-eSE-FPN-ms-3x.pth INPUT.MAX_SIZE_TEST 128
When my command line is without INPUT.MAX_SIZE_TEST
everything works fine and masks are overlaying on top of objects. Thanks!
from centermask2.
Related Issues (20)
- FCOS
- AttributeError: 'BitMasks' object has no attribute 'polygons'
- where can I find mask_rcnn_R_50_FPN_inference_acc_test.yaml
- Anyone succeed in converting pth to onnx format? HOT 1
- Anyone succeed in converting pth model to onnx format? HOT 2
- The gap between the results of our training centermask_R_101_FPN_ms_3x.yaml and the record of the paper HOT 4
- i am not familiar with detectron2 , how can i use the centermask2 in pure pytorch network defines and weights ? HOT 2
- About backbone pretrained models
- RuntimeError: nvrtc: error: invalid value for --gpu-architecture (-arch) HOT 1
- No such file or directory: 'datasets/coco/panoptic_stuff_train2017'
- Inference on random images using pre-trained models with demo.py does not produce meaningful results HOT 2
- What is the default input size for Centermask-Lite?
- how to test single image
- The difficulty in handling overlapping bounding boxes
- KeyError: "No object named 'build_fcos_vovnet_fpn_backbone' found in 'BACKBONE' registry!" HOT 9
- loss mask has remained unchanged during the training process. Why is this?
- how to use centermask-lite demo?
- May be error in MaskIOU module
- Imagenet pretrain 모델로 연락드립니다.
- on the iou loss between pred_boxes and gt_boxes
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 centermask2.