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

feat: Improved all model checkpoints and added HF hub loading function #159

Merged
merged 6 commits into from
Jul 17, 2022

Conversation

frgfm
Copy link
Member

@frgfm frgfm commented Jul 17, 2022

This PR introduces the following modifications:

  • updates all model checkpoints
  • adds their performance evaluation on OpenFire in a CSV
  • adds a model_from_hf_hub function that instantiates the model & load the parameters from the name of the HF hub repo
  • adds entry in the documentation & unittests

Closes #123

Any feedback is welcome!

@frgfm frgfm added topic: documentation Improvements or additions to documentation ext: tests Related to tests module: models Related to models ext: docs type: new feature labels Jul 17, 2022
@frgfm frgfm added this to the 0.2.0 milestone Jul 17, 2022
@frgfm frgfm requested a review from a team July 17, 2022 21:37
@frgfm frgfm self-assigned this Jul 17, 2022
@codecov
Copy link

codecov bot commented Jul 17, 2022

Codecov Report

Merging #159 (9442e99) into master (a3a73e5) will increase coverage by 0.04%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #159      +/-   ##
==========================================
+ Coverage   93.83%   93.88%   +0.04%     
==========================================
  Files           8        9       +1     
  Lines         211      229      +18     
==========================================
+ Hits          198      215      +17     
- Misses         13       14       +1     
Flag Coverage Δ
unittests 93.88% <100.00%> (+0.04%) ⬆️

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

Impacted Files Coverage Δ
pyrovision/models/mobilenetv3.py 100.00% <100.00%> (ø)
pyrovision/models/resnet.py 100.00% <100.00%> (ø)
pyrovision/models/rexnet.py 100.00% <100.00%> (ø)
pyrovision/models/utils.py 100.00% <100.00%> (ø)
pyrovision/datasets/utils.py 88.73% <0.00%> (-1.41%) ⬇️

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 a3a73e5...9442e99. Read the comment docs.

@frgfm frgfm merged commit 14887ef into master Jul 17, 2022
@frgfm frgfm deleted the model-update branch July 17, 2022 22:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ext: docs ext: tests Related to tests module: models Related to models topic: documentation Improvements or additions to documentation type: new feature
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[models] Improve the robustness of classification models againt fog occurrences
1 participant