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

[Add] Configs for QDTrack on TAO dataset. #585

Merged
merged 12 commits into from
Jun 15, 2022
Merged

[Add] Configs for QDTrack on TAO dataset. #585

merged 12 commits into from
Jun 15, 2022

Conversation

pixeli99
Copy link
Collaborator

No description provided.

@codecov
Copy link

codecov bot commented Jun 10, 2022

Codecov Report

Merging #585 (d252eb9) into master (2542848) will decrease coverage by 0.40%.
The diff coverage is 64.95%.

❗ Current head d252eb9 differs from pull request most recent head cd74d8d. Consider uploading reports for the commit cd74d8d to get more accurate results

@@            Coverage Diff             @@
##           master     #585      +/-   ##
==========================================
- Coverage   73.53%   73.12%   -0.41%     
==========================================
  Files         130      131       +1     
  Lines        8074     8189     +115     
  Branches     1564     1581      +17     
==========================================
+ Hits         5937     5988      +51     
- Misses       1648     1703      +55     
- Partials      489      498       +9     
Flag Coverage Δ
unittests 73.07% <64.95%> (-0.36%) ⬇️

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

Impacted Files Coverage Δ
mmtrack/models/trackers/quasi_dense_tao_tracker.py 64.03% <64.03%> (ø)
mmtrack/models/trackers/__init__.py 100.00% <100.00%> (ø)
mmtrack/models/trackers/quasi_dense_tracker.py 75.71% <100.00%> (ø)
mmtrack/models/trackers/tracktor_tracker.py 63.95% <0.00%> (-15.12%) ⬇️
mmtrack/datasets/pipelines/processing.py 73.93% <0.00%> (-2.43%) ⬇️
mmtrack/datasets/pipelines/transforms.py 88.99% <0.00%> (-1.38%) ⬇️

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 8b45843...cd74d8d. Read the comment docs.

@pixeli99 pixeli99 requested a review from GT9505 June 14, 2022 07:48
Copy link
Collaborator

@GT9505 GT9505 left a comment

Choose a reason for hiding this comment

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

We can merge this PR after finishing the following items:

  1. fix the comments

After this pr is merged, please create another pr to finishing the following items:

  1. use ./tools/analysis/publish_model.py to prepare the pre-trained weights of QD on TAO
  2. update the README.md and metafile.yml of QD.

configs/_base_/datasets/tao.py Outdated Show resolved Hide resolved
mmtrack/models/trackers/quasi_dense_tao_tracker.py Outdated Show resolved Hide resolved
mmtrack/models/trackers/quasi_dense_tao_tracker.py Outdated Show resolved Hide resolved
@@ -0,0 +1,47 @@
# model settings
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

need update

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

done

@pixeli99 pixeli99 requested a review from GT9505 June 15, 2022 07:33
@pixeli99 pixeli99 requested a review from GT9505 June 15, 2022 08:00
@GT9505 GT9505 merged commit d98d5fd into open-mmlab:master Jun 15, 2022
@pixeli99 pixeli99 deleted the train_tao branch June 15, 2022 14:46
GT9505 pushed a commit that referenced this pull request Jul 19, 2022
* train TAO

* update readme

* add tao tracker

* del useless files

* rollback

* fix bug

* update UT

* del useless code

* update cfg

* update file path

Co-authored-by: Pengxiang Li <lipengxiang@pjlab.org.cn>
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.

2 participants