Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FIX] Fix mistake in FASTConvLayer and tf reparameterization #1506

Merged
merged 2 commits into from
Mar 11, 2024

Conversation

felixdittrich92
Copy link
Contributor

This PR:

  • Fix mistake in FASTConvLayer (special thanks to @czczup (FAST author) for finding this mistake)
  • Fix tensorflow reparameterization
  • Provide new pretrained backbone checkpoints
  • Add small test to check that reparam works as expected

Any feedback is welcome 🤗

@odulcy-mindee Please upload the checkpoints before :)

@felixdittrich92 felixdittrich92 added type: bug Something isn't working topic: ci Related to CI module: models Related to doctr.models framework: pytorch Related to PyTorch backend framework: tensorflow Related to TensorFlow backend topic: text detection Related to the task of text detection labels Mar 11, 2024
@felixdittrich92 felixdittrich92 added this to the 0.9.0 milestone Mar 11, 2024
@felixdittrich92 felixdittrich92 self-assigned this Mar 11, 2024
@felixdittrich92 felixdittrich92 marked this pull request as ready for review March 11, 2024 08:31
@felixdittrich92
Copy link
Contributor Author

@odulcy-mindee We should check the shrink_ratio with the latest checkpoint before :)

Copy link

codecov bot commented Mar 11, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 95.82%. Comparing base (058b5db) to head (7f33b85).

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1506      +/-   ##
==========================================
- Coverage   95.84%   95.82%   -0.02%     
==========================================
  Files         166      166              
  Lines        7649     7646       -3     
==========================================
- Hits         7331     7327       -4     
- Misses        318      319       +1     
Flag Coverage Δ
unittests 95.82% <100.00%> (-0.02%) ⬇️

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

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@czczup
Copy link

czczup commented Mar 11, 2024

This is really great. Thanks for your time and effort!

Copy link
Collaborator

@odulcy-mindee odulcy-mindee left a comment

Choose a reason for hiding this comment

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

The uploaded checkpoints ;-)

doctr/models/classification/textnet/pytorch.py Outdated Show resolved Hide resolved
doctr/models/classification/textnet/pytorch.py Outdated Show resolved Hide resolved
doctr/models/classification/textnet/pytorch.py Outdated Show resolved Hide resolved
doctr/models/classification/textnet/tensorflow.py Outdated Show resolved Hide resolved
doctr/models/classification/textnet/tensorflow.py Outdated Show resolved Hide resolved
doctr/models/classification/textnet/tensorflow.py Outdated Show resolved Hide resolved
Copy link
Collaborator

@odulcy-mindee odulcy-mindee left a comment

Choose a reason for hiding this comment

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

Thanks !

@felixdittrich92 felixdittrich92 merged commit 60d4005 into mindee:main Mar 11, 2024
69 of 70 checks passed
@felixdittrich92 felixdittrich92 deleted the fix-fast branch March 11, 2024 15:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
framework: pytorch Related to PyTorch backend framework: tensorflow Related to TensorFlow backend module: models Related to doctr.models topic: ci Related to CI topic: text detection Related to the task of text detection type: bug Something isn't working
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants