Skip to content

Upgrade to mmdet 2.20.0#1041

Open
ai-fast-track wants to merge 3 commits intoairctic:masterfrom
ai-fast-track:update-to-mmdet-2.20.0
Open

Upgrade to mmdet 2.20.0#1041
ai-fast-track wants to merge 3 commits intoairctic:masterfrom
ai-fast-track:update-to-mmdet-2.20.0

Conversation

@ai-fast-track
Copy link
Collaborator

@ai-fast-track ai-fast-track commented Jan 24, 2022

I upgraded https://github.com/airctic/mmdetection_configs to mmdet 2.20.0

This PR upgrade mmdet_config_path as well as the pip install mmdet==2.20.0

closes #1040

@codecov
Copy link

codecov bot commented Jan 24, 2022 •
edited
Loading

Codecov Report

Merging #1041 (8fda0dc) into master (04644ac) will decrease coverage by 0.21%.
The diff coverage is 100.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master    #1041      +/-   ##
==========================================
- Coverage   85.93%   85.71%   -0.22%     
==========================================
  Files         278      278              
  Lines        5915     5915              
==========================================
- Hits         5083     5070      -13     
- Misses        832      845      +13
Flag Coverage Δ
unittests 85.71% <100.00%> (-0.22%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
icevision/models/mmdet/common/utils.py 81.81% <ø> (ø)
icevision/models/mmdet/download_configs.py 80.95% <100.00%> (ø)
icevision/models/inference_sahi.py 81.44% <0.00%> (-13.41%) ⬇️

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 04644ac...8fda0dc. Read the comment docs.

@dnth
Copy link
Contributor

dnth commented Jan 24, 2022 •
edited
Loading

Hi everyone, I notice that with mmdet==2.20.0 the VFNet fails to train with the following error. Any mmdet version above 2.17.0 shows the same error.

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-16-35383c9197b5> in <module>()
----> 1 learn.fine_tune(20, 0.00158, freeze_epochs=1)

21 frames
/usr/local/lib/python3.7/dist-packages/mmcv/runner/fp16_utils.py in new_func(*args, **kwargs)
    184                                 'method of nn.Module')
    185             if not (hasattr(args[0], 'fp16_enabled') and args[0].fp16_enabled):
--> 186                 return old_func(*args, **kwargs)
    187             # get the arg spec of the decorated method
    188             args_info = getfullargspec(old_func)

TypeError: loss() missing 1 required positional argument: 'img_metas'

Here is a Colab notebook I ran
https://colab.research.google.com/github/airctic/icevision/blob/master/notebooks/getting_started_object_detection.ipynb

@potipot
Copy link
Contributor

potipot commented Jan 24, 2022

I can confirm having the same error

potipot
potipot requested changes Jan 26, 2022
View reviewed changes
Copy link
Contributor

@potipot potipot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the error mentioned in PR comments needs to be addressed

@ai-fast-track
Copy link
Collaborator Author

ai-fast-track commented Jan 27, 2022

@dnth @potipot I experienced the same issue. We need to investigate that!

This was referenced Jan 29, 2022
Merged
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@potipot potipot potipot requested changes

@fstroth fstroth Awaiting requested review from fstroth

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Upgrade to mmdet 2.20.0

3 participants

@ai-fast-track @dnth @potipot