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

[references] Add poly scheduler for detection training #1444

Merged
merged 4 commits into from
Feb 2, 2024

Conversation

felixdittrich92
Copy link
Contributor

This PR:

  • Add Polynomial Scheduler for detection training (TF & PT)
  • It's often mentioned in text detection papers like DB & FAST & .. so i think it is a good idea to add it :)

Any feedback is welcome 🤗

@felixdittrich92 felixdittrich92 added type: enhancement Improvement ext: references Related to references folder framework: pytorch Related to PyTorch backend framework: tensorflow Related to TensorFlow backend topic: text detection Related to the task of text detection labels Jan 30, 2024
@felixdittrich92 felixdittrich92 added this to the 0.8.0 milestone Jan 30, 2024
@felixdittrich92 felixdittrich92 self-assigned this Jan 30, 2024
Copy link

codecov bot commented Jan 30, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (f5445ef) 95.81% compared to head (c996c1b) 95.80%.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1444      +/-   ##
==========================================
- Coverage   95.81%   95.80%   -0.02%     
==========================================
  Files         162      162              
  Lines        7101     7101              
==========================================
- Hits         6804     6803       -1     
- Misses        297      298       +1     
Flag Coverage Δ
unittests 95.80% <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.

odulcy-mindee added a commit to odulcy-mindee/doctr that referenced this pull request Feb 1, 2024
@felixdittrich92
Copy link
Contributor Author

@odulcy-mindee I think with choices it's more clean instead of raising an exception :)
Switched the default to poly -> (After testing LinkNet / DB & FAST on 2 different detection datasets x Poly / Cosine / Onecycle -> Poly has reached the best results with mostly no drops)

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.

Yeah, it's better with choices, thanks !

@felixdittrich92 felixdittrich92 merged commit 98cd0e9 into mindee:main Feb 2, 2024
68 of 69 checks passed
@felixdittrich92 felixdittrich92 deleted the poly branch February 2, 2024 10:21
odulcy-mindee added a commit to odulcy-mindee/doctr that referenced this pull request Feb 7, 2024
odulcy-mindee added a commit to odulcy-mindee/doctr that referenced this pull request Feb 28, 2024
odulcy-mindee added a commit to odulcy-mindee/doctr that referenced this pull request Mar 4, 2024
odulcy-mindee added a commit to odulcy-mindee/doctr that referenced this pull request Mar 5, 2024
odulcy-mindee added a commit to odulcy-mindee/doctr that referenced this pull request Mar 11, 2024
odulcy-mindee added a commit to odulcy-mindee/doctr that referenced this pull request Mar 26, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ext: references Related to references folder framework: pytorch Related to PyTorch backend framework: tensorflow Related to TensorFlow backend topic: text detection Related to the task of text detection type: enhancement Improvement
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants