search

Zhongdao / UniTrack

[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).
MIT License
338 stars 34 forks source link

problem with the module yolox #12

Open tulbureandreit opened 3 years ago

tulbureandreit commented 3 years ago

Hello, after following the install.md I received the error: no module yolox found. I did: pip install yolox and then I receive no module found: yolox.data

Any suggestions?

Zhongdao commented 3 years ago

Hi, Could you try the following commands? cd detector/YOLOX pip install -U pip && pip install -r requirements.txt pip install -v -e .

tulbureandreit commented 3 years ago

Solved this problem. Thank you!

I encountered many other after this, mainly because I couldn`t directly run python demo/demo_mot.py

I needed to update the path for many args, @ everybody shall be careful about that and double check args and args path (ex: weights or input video)

Moreover, if you have CUDA 11.2 and PyTorch 1.9.0 it seems that you get this error:" RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. sh: 1: ffmpeg: not found"

Potential solution: reinstall or make a new conda env with python3.7, pytorch 1.8.0 and <=cuda 11.1 conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=11.1 -c pytorch -c conda-forge

I will update on it

tulbureandreit commented 3 years ago

Solved this problem. Thank you!

I encountered many other after this, mainly because I couldn`t directly run python demo/demo_mot.py

I needed to update the path for many args, @ everybody shall be careful about that and double check args and args path (ex: weights or input video)

Moreover, if you have CUDA 11.2 and PyTorch 1.9.0 it seems that you get this error:" RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. sh: 1: ffmpeg: not found"

Potential solution: reinstall or make a new conda env with python3.7, pytorch 1.8.0 and <=cuda 11.1 conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=11.1 -c pytorch -c conda-forge

I will update on it

Yes, reinstalling cudatoolkit=11.1 solved it.