open-mmlab / mmselfsup

OpenMMLab Self-Supervised Learning Toolbox and Benchmark
https://mmselfsup.readthedocs.io/en/latest/
Apache License 2.0
3.18k stars 428 forks source link

[Refactor] Refactor t-SNE #629

Closed fangyixiao18 closed 1 year ago

fangyixiao18 commented 1 year ago

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Refactor t-SNE to support more backbones, like ViT, Swin, etc.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduce changes that break the backward compatibility of the downstream repositories? If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here and update the documentation.

Checklist

Before PR:

After PR:

YuanLiuuuuuu commented 1 year ago

We can move all feature analysis tools to MMClassification, and provide an unified entrance later.

codecov[bot] commented 1 year ago

Codecov Report

Base: 81.61% // Head: 81.63% // Increases project coverage by +0.02% :tada:

Coverage data is based on head (548b7ca) compared to base (fbe0ff6). Patch coverage: 100.00% of modified lines in pull request are covered.

:exclamation: Current head 548b7ca differs from pull request most recent head 60584cf. Consider uploading reports for the commit 60584cf to get more accurate results

Additional details and impacted files ```diff @@ Coverage Diff @@ ## dev-1.x #629 +/- ## =========================================== + Coverage 81.61% 81.63% +0.02% =========================================== Files 135 135 Lines 4961 4961 Branches 672 672 =========================================== + Hits 4049 4050 +1 Misses 774 774 + Partials 138 137 -1 ``` | Flag | Coverage Δ | | |---|---|---| | unittests | `81.63% <100.00%> (+0.02%)` | :arrow_up: | Flags with carried forward coverage won't be shown. [Click here](https://docs.codecov.io/docs/carryforward-flags?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=open-mmlab#carryforward-flags-in-the-pull-request-comment) to find out more. | [Impacted Files](https://codecov.io/gh/open-mmlab/mmselfsup/pull/629?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=open-mmlab) | Coverage Δ | | |---|---|---| | [mmselfsup/datasets/samplers/deepcluster\_sampler.py](https://codecov.io/gh/open-mmlab/mmselfsup/pull/629/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=open-mmlab#diff-bW1zZWxmc3VwL2RhdGFzZXRzL3NhbXBsZXJzL2RlZXBjbHVzdGVyX3NhbXBsZXIucHk=) | `95.83% <100.00%> (ø)` | | | [mmselfsup/datasets/transforms/processing.py](https://codecov.io/gh/open-mmlab/mmselfsup/pull/629/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=open-mmlab#diff-bW1zZWxmc3VwL2RhdGFzZXRzL3RyYW5zZm9ybXMvcHJvY2Vzc2luZy5weQ==) | `89.00% <100.00%> (+0.21%)` | :arrow_up: | Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=open-mmlab). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=open-mmlab)

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.