WXinlong / SOLO

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
Other
1.69k stars 307 forks source link

SOLO is working fine till pytorch version 1.4!!! #99

Open abubakar2141731 opened 4 years ago

abubakar2141731 commented 4 years ago

Thanks for your error report and we appreciate it a lot.

Checklist

  1. I have searched related issues but cannot get the expected help.
  2. The bug has not been fixed in the latest version.

Describe the bug SOLO installation is working fine till pytorch version 1.4, it is not geting installed properly wiht the higher versions, kindly update the read me , so people won't have much trouble, i spent more than two days , on finding the right match of pytorch to install solo!!!

Reproduction

  1. What command or script did you run?
    A placeholder for the command.
  2. Did you make any modifications on the code or config? Did you understand what you have modified?
  3. What dataset did you use?

Environment

  1. Please run python tools/collect_env.py to collect necessary environment infomation and paste it here.
  2. You may add addition that may be helpful for locating the problem, such as
    • How you installed PyTorch [e.g., pip, conda, source]
    • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

WXinlong commented 4 years ago

@abubakar2141731 Thanks for pointing it out. I will update the doc.

wuyuanyi135 commented 3 years ago

I can confirm the issue reported by the author. The cause was that SOLO\mmdet\ops\nms\src\nms_cuda.cpp(9): error C3861: 'AT_CHECK': identifier not found. I believe this deprecation needs to be updated.