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

[demo] remove limitation and update demo #1390

Merged
merged 5 commits into from
Nov 24, 2023

Conversation

felixdittrich92
Copy link
Contributor

This PR:

  • removes the limitation so that all models can also be used for possible rotated inputs
  • updates the demo and add some more options

Any feedback is welcome 🤗

@felixdittrich92 felixdittrich92 added this to the 0.8.0 milestone Nov 23, 2023
@felixdittrich92 felixdittrich92 self-assigned this Nov 23, 2023
@felixdittrich92 felixdittrich92 added type: enhancement Improvement module: models Related to doctr.models ext: demo Related to demo folder topic: text detection Related to the task of text detection labels Nov 23, 2023
Copy link

codecov bot commented Nov 23, 2023

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (419ea05) 95.77% compared to head (7f18cd1) 95.79%.
Report is 1 commits behind head on main.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1390      +/-   ##
==========================================
+ Coverage   95.77%   95.79%   +0.02%     
==========================================
  Files         155      155              
  Lines        6951     6942       -9     
==========================================
- Hits         6657     6650       -7     
+ Misses        294      292       -2     
Flag Coverage Δ
unittests 95.79% <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.

@felixdittrich92 felixdittrich92 marked this pull request as ready for review November 23, 2023 10:17
"mean": (0.798, 0.785, 0.772),
"std": (0.264, 0.2749, 0.287),
"input_shape": (1024, 1024, 3),
"url": "https://doctr-static.mindee.com/models?id=v0.6.0/linknet_resnet18-611b50f2.zip&src=0",
Copy link
Collaborator

Choose a reason for hiding this comment

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

This one should be kept and remove the other one ?

Copy link
Contributor

Choose a reason for hiding this comment

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

Mh it's the same arch so i changed the chekpoint because the sec one was already trained on rotated samples so while finetuning it should converge faster as the checkpoint which wasn't trained with rotated samples :)

Makes only sense for TF because the change to antialias=True was much less changing as compared to pytorch

Copy link
Contributor

Choose a reason for hiding this comment

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

In the end we'll train it anyway ^^

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 3b99d46 into mindee:main Nov 24, 2023
67 checks passed
@felixdittrich92 felixdittrich92 deleted the remove-rot-limitation branch November 24, 2023 12:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ext: demo Related to demo folder module: models Related to doctr.models 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.

None yet

3 participants