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

Refine recipes for classification #3776

Merged

Conversation

harimkang
Copy link
Contributor

@harimkang harimkang commented Jul 30, 2024

Summary

      Small   Medium   Large  
Task Model otx_version Test/Accuracy Train/e2e_time Test/Accuracy Train/e2e_time Test/Accuracy Train/e2e_time
MULTI_CLASS_CLS deit_tiny develop 1.0 19 0.7831 38 0.8385 436
    This PR 1.0 11 0.7998 89 0.8540 263
  dino_v2 develop 0.9842 40 0.8435 206 0.8960 883
    This PR 1.0 15 0.8428 245 0.8972 847
  efficientnet_b0 develop 0.9989 19 0.7704 116 0.8338 288
    This PR 1.0 10 0.7819 88 0.8338 296
  efficientnet_v2 develop 0.9966 26 0.8525 123 0.8854 434
    This PR 1.0 17 0.8577 148 0.8878 564
  mobilenet_v3_large develop 0.9842 18 0.7733 105 0.8246 401
    This PR 0.9831 10 0.7889 63 0.8263 265

How to test

Checklist

  • I have added unit tests to cover my changes.​
  • I have added integration tests to cover my changes.​
  • I have ran e2e tests and there is no issues.
  • I have added the description of my changes into CHANGELOG in my target branch (e.g., CHANGELOG in develop).​
  • I have updated the documentation in my target branch accordingly (e.g., documentation in develop).
  • I have linked related issues.

License

  • I submit my code changes under the same Apache License that covers the project.
    Feel free to contact the maintainers if that's a concern.
  • I have updated the license header for each file (see an example below).
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

@harimkang harimkang changed the title Recipe refinement for Classification Refine recipes for classification Jul 30, 2024
@harimkang harimkang marked this pull request as ready for review July 31, 2024 04:58
@sungchul2
Copy link
Contributor

sungchul2 commented Jul 31, 2024

Actually, it is no problem for validation and test transforms in the above comments because otx ignores if there are no override components although those keys are set in reset.
But I think it should be updated because it is the example that users can refer to for their own recipes.

@harimkang harimkang added this pull request to the merge queue Jul 31, 2024
Merged via the queue into openvinotoolkit:develop with commit f2f0cdc Jul 31, 2024
18 checks passed
@harimkang harimkang deleted the harimkan/refactor-recipe-cls branch July 31, 2024 09:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants