Mmcv-and-mmcls-compatible #1

ccanamero · 2024-08-20T11:47:41Z

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

Please describe the motivation of this PR and the goal you want to achieve through this PR.

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:

Pre-commit or other linting tools are used to fix the potential lint issues.
Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects, like MMDet or MMSeg.
CLA has been signed and all committers have signed the CLA in this PR.

* [Feature] Support MPS device. * Add `auto_select_device` * Add unit tests

* Fix albu BUG: using albu will cause the label from array(x) to array([x]) and crash the trainning * Fix common * Using copy incase potential bug in multi-label tasks * Improve coding * Improve code logic * Add unit test * Fix typo * Fix yapf

* [Feature] Support MViT. * Add MViT configs and docs * Add unit test * Fix unit tests.

* init rough try for modify * Init swin transform v2 * lint * reformat * init config * refactor * update config * fix test * add doc * refact * add model meta * rename config * add doc * fix meta model name * restruct * rename embed_bims to out_channels * fix ut and update model

* [Fix] Fix the output position of Swin-Transformer. * Rename `downsample` argument to `do_downsample`.

* Support CSRA head. * Add CSRA config. * Improve training scheduler and Update cfg, ckpt, log * Update metafile * Rename config files and checkpoints Co-authored-by: Ezra-Yu <[email protected]> Co-authored-by: mzr1996 <[email protected]>

* Update regnet.py In the example comment to print out the different layers of outputs, we need to indicate the `out_indices` to (0,1,2,3) to see all backbone layers output as the default argument is (3,) * Update regnet.py following changes proposal of maintainer * fix linting * fix blank space for docs * fix blank space for docs * fix blank space for docs

…pen-mmlab#964) * fix precise BN hook when using MLU * fix unit tests

* feat: add stanford car dataset * feat: add stanford car dataset * feat: add stanford car dataset * feat: add stanford car dataset * feat: add stanford car dataset * feat: add stanford car dataset * Update links and using cars insteam of car * place ependency scipy from runtime to optional * Fix docstring Co-authored-by: Ezra-Yu <[email protected]> Co-authored-by: mzr1996 <[email protected]>

* add efficient backbone * Update Readme and metafile * Add unit tests * fix confict * fix lint * update efficientformer head unit tests * update README * fix unit test * fix Readme * fix example * fix typo * recover api modification * Update EfficiemtFormer Backbone * fix unit tests * add efficientformer to readme and model zoo

* [Improve] Use `forward_dummy` to calculate FLOPS. (open-mmlab#953) * fixed Co-authored-by: Ming-Hsuan-Tu <[email protected]>

…tion. (open-mmlab#965)

…mmlab#1032) * [Feature] update the issue template with more links and emoji * fix lint error * Use yaml format issue templates. * Update template Co-authored-by: mzr1996 <[email protected]>

* update van * fix init * b4 result * update van * keep old config * keep old config * fix metafile * update VAN configs * update example Co-authored-by: Ezra-Yu <[email protected]>

* add hornet * add hornet * add hornet * add hornet * add hornet * add hornet * add hornet * fix test for torch before 1.7.0 * del timm * fix readme * fix readme * Update mmcls/models/backbones/hornet.py Co-authored-by: Ezra-Yu <[email protected]> * fix docs * fix docs * s -> scale * fix dims and dpr impl * fix layer scale * refactor gnconv * add dw_cfg * add convert tools * update code * update docs * update readme * update URLs Co-authored-by: Ezra-Yu <[email protected]>

…mlab#901) * futher detail for the doc for datasets/dataset_wrappers/ClassBalancedDataset * fix

* [Docs] Fixed typo in pytorch2torchscript.md * [Docs] Fixed W293 blank line contains whitespace

…1152) * Support Activation Checkpointing for ConvNeXt * Add test case * Lint * Add docstring

* Training on MLU is available

…1215)

…ts. (open-mmlab#1218) * update npu results * add dist_train_arm.sh & updata docs * del content

…mlab#1216)

…n README (open-mmlab#1443) * upodate README * fix typo

…#1650)

* [Improve]Enable binary operators on the NPU. * Update docs link --------- Co-authored-by: mzr1996 <[email protected]>

mzr1996 and others added 30 commits June 22, 2022 17:28

[CI] Add test mim CI. (open-mmlab#879)

812f3d4

[Fix] Remove duplicated wide-resnet metafile.

11df205

[Feature] Support MPS device. (open-mmlab#894)

c03efee

* [Feature] Support MPS device. * Add `auto_select_device` * Add unit tests

[Fix] Fix Albu crash bug. (open-mmlab#918)

00f0e0d

* Fix albu BUG: using albu will cause the label from array(x) to array([x]) and crash the trainning * Fix common * Using copy incase potential bug in multi-label tasks * Improve coding * Improve code logic * Add unit test * Fix typo * Fix yapf

Bump version to 0.23.2. (open-mmlab#937)

9300cc4

Merge remote-tracking branch 'origin/dev'

71ef7ba

[Feature] Support MViT and add checkpoints. (open-mmlab#924)

556fa56

* [Feature] Support MViT. * Add MViT configs and docs * Add unit test * Fix unit tests.

[Fix] Fix the output position of Swin-Transformer. (open-mmlab#947)

b5bb86a

* [Fix] Fix the output position of Swin-Transformer. * Rename `downsample` argument to `do_downsample`.

[Feature] Support CSRA head. (open-mmlab#881)

1a3d51a

* Support CSRA head. * Add CSRA config. * Improve training scheduler and Update cfg, ckpt, log * Update metafile * Rename config files and checkpoints Co-authored-by: Ezra-Yu <[email protected]> Co-authored-by: mzr1996 <[email protected]>

[Improve] Use forward_dummy to calculate FLOPS. (open-mmlab#953)

90254a8

[Imporve] Using train_step instead of forward in PreciseBNHook (o…

e54cfd6

…pen-mmlab#964) * fix precise BN hook when using MLU * fix unit tests

Merge remote-tracking branch 'origin/master' into dev

5ad3bed

[Improve] Fixed typo in RepVGG. (open-mmlab#985)

ec71d07

* [Improve] Use `forward_dummy` to calculate FLOPS. (open-mmlab#953) * fixed Co-authored-by: Ming-Hsuan-Tu <[email protected]>

[Fix] Fix device mismatch in Swin-v2. (open-mmlab#976)

517bd3d

Update README

982cab4

[Improve] Upgrade onnxsim to v0.4.0. (open-mmlab#915)

6d8c918

[Refactor] Re-write get_sinusoid_encoding from third-party implementa…

0b4a67d

…tion. (open-mmlab#965)

[Docs] Fix typo for wrong reference. (open-mmlab#1036)

8d1bc55

[Doc] Fix typo in tutorial 2 (open-mmlab#1043)

a1b644b

[Docs] Fix a typo in ImageClassifier (open-mmlab#1050)

75ae845

[Feature] Update the issue template with more links and emoji. (open-…

c94e9b3

…mmlab#1032) * [Feature] update the issue template with more links and emoji * fix lint error * Use yaml format issue templates. * Update template Co-authored-by: mzr1996 <[email protected]>

[Fix] Fix attenstion clamp max params (open-mmlab#1034)

6ebb3f7

[Enhancement] Update VAN. (open-mmlab#1017)

56589ee

* update van * fix init * b4 result * update van * keep old config * keep old config * fix metafile * update VAN configs * update example Co-authored-by: Ezra-Yu <[email protected]>

[Fix] Fix config.device bug in toturial. (open-mmlab#1059)

4d73607

[Fix] val loader should not drop last by default. (open-mmlab#857)

0143e5f

mzr1996 and others added 30 commits November 1, 2022 14:19

Merge branch 'dev'

8c63bb5

[Docs] further detail for the doc for ClassBalancedDataset. (open-m…

aacaa73

…mlab#901) * futher detail for the doc for datasets/dataset_wrappers/ClassBalancedDataset * fix

[Docs] Fix typo in miscellaneous.md. (open-mmlab#1137)

9b1cd5c

[Docs] Fixed typo in pytorch2torchscript.md (open-mmlab#1173)

4a3ad4f

* [Docs] Fixed typo in pytorch2torchscript.md * [Docs] Fixed W293 blank line contains whitespace

[Feature] Support Activation Checkpointing for ConvNeXt. (open-mmlab#…

05e4bc1

…1152) * Support Activation Checkpointing for ConvNeXt * Add test case * Lint * Add docstring

[Docs] Update NPU support doc. (open-mmlab#1198)

0eb3b61

[Feature] Support MLU backend. (open-mmlab#1159)

dc8691e

* Training on MLU is available

[Fix] Fix the redundant device_ids in tools/test.py. (open-mmlab#…

96bb2dd

…1215)

[Enhance] Add dist_train_arm.sh for ARM device and update NPU resul…

578c035

…ts. (open-mmlab#1218) * update npu results * add dist_train_arm.sh & updata docs * del content

[Docs] Add version banner and version warning in master docs. (open-m…

8387358

…mlab#1216)

[Fix] Fix a bug caused MMClsWandbHook stuck. (open-mmlab#1242)

3e99395

Bump version to v0.25.0. (open-mmlab#1244)

c737e65

Merge branch 'dev'

2495400

[CI] Update CI of the master branch. (open-mmlab#1252)

7bf42ee

[Bot] Update assignee schedule. (open-mmlab#1262)

48fdcdb

[Docs] Fix the wrong VGG-16-BN config link in Model-Page.

3d4f80d

Fix docs

fb16bdc

[DOC] Update recommended branch from MMClassification to MMPreTrain i…

f2adad2

…n README (open-mmlab#1443) * upodate README * fix typo

[Fix]Fix the issue where 1p cannot specify a card number. (open-mmlab…

748ab7a

…#1650)

[Improve] Enable binary operators on the NPU. (open-mmlab#1714)

4ec2509

* [Improve]Enable binary operators on the NPU. * Update docs link --------- Co-authored-by: mzr1996 <[email protected]>

Nuevo repo mmpretrain

09c46f5

Adding MultiScaleFlipAug and changing directories

737880c

Update __init__

877eb38

albumentaions new version

521c164

img_scale param

9e55795

img_scale argument for Resize function

00ee948

Adding keep ration to Resize function

e2241da

Argument size now is optional

434021b

New changes managing multichannel

3c59c2b

Update build_dataset function

24e970e

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Mmcv-and-mmcls-compatible #1

Mmcv-and-mmcls-compatible #1

ccanamero commented Aug 20, 2024

Mmcv-and-mmcls-compatible #1

Are you sure you want to change the base?

Mmcv-and-mmcls-compatible #1

Conversation

ccanamero commented Aug 20, 2024

Motivation

Modification

BC-breaking (Optional)

Use cases (Optional)

Checklist