Comments (4)
i got it too..Segmentation fault(core dumped). Have you solve it?
from fairmot.
Have you successfully built DCNv2?I think the error is caused by "You're using a third-party extension module written in C, and that extension module has crashed." You can try to build DCNv2 again or use our HRNetW18 model which does not need DCNv2 to run the demo (don't forget to comment the lines with 'dcn' in src/lib/models/model.py).
from fairmot.
i got it too..Segmentation fault(core dumped). Have you solve it?
have you solve this problem,i locate the problem caused by dcnv2,but how to solve it
from fairmot.
Have you successfully built DCNv2?I think the error is caused by "You're using a third-party extension module written in C, and that extension module has crashed." You can try to build DCNv2 again or use our HRNetW18 model which does not need DCNv2 to run the demo (don't forget to comment the lines with 'dcn' in src/lib/models/model.py).
@ifzhang How to use HRNetW18 model correctly? I use following command:
python track.py mot --load_model ../models/hrnetv2_w18_imagenet_pretrained.pth --conf_thres 0.6 --val_mot16 False
Got following warning:
No param reg.2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
No param reg.2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
and all NaN value ...
from fairmot.
Related Issues (20)
- What's the different between pre-trained and baseline model?
- Has anyone ever run fairmot's dla network in CMU panoptic?
- YOLOV5
- Error of running demo.py HOT 1
- No validation set was used for training
- RuntimeError: read(): fd 3 failed with Permission denied
- Why is this happening?
- Number of unique track ids in dataset zoo HOT 3
- RuntimeError: Error compiling objects for extension
- ModuleNotFoundError: No module named 'dcn_v2' HOT 3
- How to adjust detection box size?
- how to convert the images into video?
- Partial Human Body Tracking HOT 2
- Why do you filter ground truth data on the condition h > 0 and w > 0 in the JointDataset. HOT 1
- NaN id loss while training your custom dataset HOT 2
- Update 2DMOT15 references to MOT15 and fix broken link
- Default mot just installed using baseline
- How to add a plug-in
- Where can I find the pretrained dla34 model without dcn?
- ModuleNotFoundError: No module named '_ext'
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 fairmot.