mirrors
/
mmpretrain
mirror of https://github.com/open-mmlab/mmpretrain.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
623 Commits
8 Branches
41 Tags
32 MiB
Commit Graph

92 Commits (2495400a98a3da9bd8cfb3731a711f4c77cc56a3)

Author SHA1 Message Date
mzr1996 2495400a98 Merge branch 'dev' 2022-12-06 18:25:47 +08:00
TangYueran dc8691e889
[Feature] Support MLU backend. (#1159) 
* Training on MLU is available
 2022-11-15 17:02:16 +08:00
unseenme 4a3ad4f652
[Docs] Fixed typo in pytorch2torchscript.md (#1173) 
* [Docs] Fixed typo in pytorch2torchscript.md

* [Docs] Fixed W293 blank line contains whitespace
 2022-11-09 11:03:12 +08:00
JayChen aacaa7316c
[Docs] further detail for the doc for `ClassBalancedDataset`. (#901) 
* futher detail for the doc for datasets/dataset_wrappers/ClassBalancedDataset

* fix
 2022-11-02 17:52:58 +08:00
wangjiangben-hw 17ed870fd1
[Feature] Support mmcls with NPU backend. (#1072) 
* init npu

* Avoid to import latest MMCV code to be compatible with old verisons.

Co-authored-by: mzr1996 <mzr1996@163.com>
 2022-10-24 11:45:14 +08:00
zzc98 7b16bcdd9b
[Feature] Support Stanford Cars dataset. (#893) 
* 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 <1105212286@qq.com>
Co-authored-by: mzr1996 <mzr1996@163.com>
 2022-08-16 11:14:17 +08:00
JiayuXu 1a3d51acc2
[Feature] Support CSRA head. (#881) 
* 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 <1105212286@qq.com>
Co-authored-by: mzr1996 <mzr1996@163.com>
 2022-08-04 18:15:51 +08:00
HinGwenWoong 00f0e0d0be
[Fix] Fix Albu crash bug. (#918) 
* 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
 2022-07-28 14:10:34 +08:00
mzr1996 1d6fbe0efe [Fix] Fix lint and mmcv version requirement for IPU. 2022-04-29 22:33:29 +08:00
Hu Di b4eefe4794
[Enhance] Support training on IPU and add fine-tuning configs of ViT. (#723) 
* implement training and evaluation on IPU

* fp16 SOTA

* Tput reaches 5600

* 123

* add poptorch dataloder

* change ipu_replicas to ipu-replicas

* add noqa to config long line(website)

* remove ipu dataloder test code

* del one blank line in test_builder

* refine the dataloder initialization

* fix a typo

* refine args for dataloder

* remove an annoted line

* process one more conflict

* adjust code structure in mmcv.ipu

* adjust ipu code structure in mmcv

* IPUDataloader to IPUDataLoader

* align with mmcv

* adjust according to mmcv

* mmcv code structre fixed

Co-authored-by: hudi <dihu@graphcore.ai>
 2022-04-29 22:22:19 +08:00
Ma Zerun 702c196514
[Docs] Refine API reference. (#774) 
* [Docs] Refine API reference

* Add PoolFormer
 2022-04-15 20:19:20 +08:00
Ma Zerun d0d6f73fab
[Feature] Add `CustomDataset`. (#738) 
* Add custom dataset and refactor ImageNet dataset

* Add default CLASSES for CIFAR dataset

* Add unit tests

* Imporve according to comments
 2022-03-30 15:28:26 +08:00
Hubert 995f2912ab
[Feature] Add diff seeds to diff ranks. (#744) 
* [Feature] Add diff seeds to diff ranks.

* lint
 2022-03-25 15:31:13 +08:00
huyu a19c28fe95
[Enhance] Add `get_cat_ids` and `get_gt_labels` to KFoldDataset. (#721) 2022-03-23 15:57:36 +08:00
Ma Zerun 7856141132
[Enhance] Set torch seed in `worker_init_fn` (#733) 2022-03-16 23:12:57 +08:00
takuoko aa522f4309
[Feature] Support CUB dataset. (#703) 
* support cub dataset

* support cub dataset

* fix train lint error

* add docs

* fix class label

Co-authored-by: Ezra-Yu <1105212286@qq.com>

* del debug code

* skip docformatter problem

* add unit tests

* add CUB baseline configs and chpts

* fix some typos

* fix name style

* update flops

Co-authored-by: Ezra-Yu <1105212286@qq.com>
 2022-03-16 16:22:28 +08:00
Ma Zerun 1a28f9ace6
[Feature] Add `evaluate` function for ConcatDataset. (#650) 
* Add `evaluate` function for ConcatDataset

* Remove newline in log.

* Fix lint

* Specify mmcv version in Windows CI
 2022-02-28 12:46:17 +08:00
Ma Zerun fcd57913ae
[Enhance] Upgrade isort pre-commit hooks. (#687) 
* Use new version flake8 and isort hooks

* Fix missing copyright
 2022-02-17 02:17:20 +08:00
Ma Zerun bca695b684
[Refactor] Remove deprecation. (#633) 
* Remove deprecated `--options` in some tools

* Remove deprecated eval hooks and fp16 hooks

* Remove deprecated mixup&cutmix, pretrained and return_tuple arguments.

* Remove deprecated `deprecated_options` in multi label dataset

* Remove deprecated `formating.py`

* Remove deprecated default mode of `LabelSmoothLoss`

* Revert pretrained argument, and remove it's deprecation sign.

* Update unit test
 2022-02-10 09:30:18 +08:00
xiatao 8488a784f0
[Fix] Fix potential unexcepted behaviors if `metric_options` is not specified in multi-label evaluation. (#647) 
* Update multi_label.py

* Fix lint

Co-authored-by: mzr1996 <mzr1996@163.com>
 2022-01-27 10:27:38 +08:00
Ma Zerun b39885d953
[Feature] Support K-fold cross-validation (#563) 
* Support to use `indices` to specify which samples to evaluate.

* Add KFoldDataset wrapper

* Rename 'K' to 'num_splits' accroding to sklearn

* Add `kfold-cross-valid.py`

* Add unit tests

* Add help doc and docstring
 2022-01-19 18:32:55 +08:00
Zhicheng Chen da39ca6898
[Fix] Fix test sampler bug. (#611) 
* sampler bugfixes

* sampler bugfixes

* reorganize code

* minor fixes

* reorganize code

* minor fixes

* Use `mmcv.runner.get_dist_info` instead of `dist` package to get rank
and world size.

* Add `build_dataloader` unit tests and fix sampler's unit tests.

* Fix unit tests

* Fix unit tests

Co-authored-by: mzr1996 <mzr1996@163.com>
 2021-12-23 18:07:41 +08:00
Zhicheng Chen d5ae255061
[Feature] Repeated Aug and Sampler Registry (#588) 2021-12-21 15:26:28 +08:00
mzr1996 5078869b4b [Fix] Fix cal_acc bug caused by the return type of accuracy. 2021-12-14 16:21:25 +08:00
Ma Zerun e3cf1881bb
[Enhance] Imporve efficiency of precision, recall, f1_score and support. (#595) 
* [Enhance] Imporve efficiency of precision, recall, f1_score and support.

* Fix bugs

* Use np.maximum since torch doesn't have maximum before torch 1.7

* Fix bug
 2021-12-13 17:24:59 +08:00
Ma Zerun f2c1c57398
[Docs] Fix docs build dependency. (#584) 
* Fix docs.

* Add MMHuman3D
 2021-12-07 11:16:33 +08:00
Ezra-Yu 4b2128fdbd
[Fix] Fix bug when using `ClassBalancedDataset` (#555) 
* fix dataset wrapper bug and add unit tests

* fix dataset wrapper bug and add unit tests

* update unit tests

* fix lint

* align interface to mmdet

* update unit tests
 2021-11-26 09:40:00 +08:00
LeoXing1996 49cbfd776a
[Fix] Fix interpolation method checking in `Resize` (#547) 
* fix interpolation method checking in resize

* revise docstring + add unit test
 2021-11-19 17:38:25 +08:00
Zhicheng Chen 9ab9d4ff31
[Refactor] Refactor `Resize` transform and add `Pad` transform. (#506) 
* refactor resize, test tobe done

* resize reimpl according to discussion; add pad

* minor fixes and add tests

* minor fixes on docstring

* add additional unit test

* reformat resize and pad

* revise code and docstr according to the comments
 2021-11-10 16:46:49 +08:00
Ma Zerun fffa30dd48
[Feature] Add Tokens-to-Token ViT backbone and converted checkpoints. (#467) 
* add t2t backbone

* register t2t_vit

* add t2t_vit config

* [Temp] Align posterize transform with timm.

* Fix lint

* Refactor t2t-vit

* Add config for t2t-vit

* Add metafile and README for t2t-vit

* Add unit tests

* configs

* Update metafile and README

* Improve docstring

* Fix batch size which should be 8x64 instead of 8x128

* Fix typo

* Update model zoo

* Update training augments config.

* Move some arguments of T2TModule to T2TViT

* Update docs.

* Update unit test

Co-authored-by: HIT-cwh <2892770585@qq.com>
 2021-10-29 10:37:16 +08:00
Ezra-Yu 2ce5825ef1
[Feature] Support ImageNet21k dataset. (#461) 
* add imagnet21k

* Update unit test

* update imaenet21k

* use slots

* use slots

* rename Data_item to ImageInfo

* add unit tests

* Update unit tests

* rm some print

* update unit tests

* fix lint

* remove default value of pipeline
 2021-10-28 15:22:08 +08:00
imyhxy 671414becb
[Fix] Fix missing import `Compose` and `Normalize`. 
* Fixed missing import 'Compose'

* Fixed mistype `Compose` in `mmcls/datasets/__init__.py`

* Fixed missing import `Normalize`

* [Docs] Fix typos in doctest

* [Fix] Sort import module
 2021-10-28 15:21:05 +08:00
Ma Zerun 7eeb54ce9c
[Fix] Fix version check in dataset builder. (#474) 
* Fix version check in dataset builder.

* Use mmcv version check function.
 2021-10-13 14:34:56 +08:00
Ma Zerun 2e6c7cf87d
[Docs] Add code-spell pre-commit hook and fix a large mount of typos. (#470) 
* Add code spell check hook

* Add codespell config

* Fix a lot of typos.

* Add formating.py to keep compatibility.
 2021-10-13 14:33:07 +08:00
Ezra-Yu f865c725f2
[Docs] Fix typo in transforms.py docstring (#455) 2021-09-22 11:09:23 +08:00
Charlyo 8024f81de2
[Docs] Fix a typo in transforms (#454) 2021-09-22 10:46:59 +08:00
Ma Zerun 6a0a76af0c
[Enhance] Add `hparams` argument in `AutoAugment` and `RandAugment` and some other improvement. (#398) 
* Add hparams argument in `AutoAugment` and `RandAugment`.

And `pad_val` supports sequence instead of tuple only.

* Add unit tests for `AutoAugment` and `hparams` in `RandAugment`.

* Use smaller test image to speed up uni tests.

* Use hparams to simplify RandAugment config in swin-transformer.

* Rename augment config name from `pipeline` to `pipelines`.

* Add some commnet ad docstring.
 2021-08-24 18:15:54 +08:00
Ma Zerun f9eb9b409b
[Docs] Add Copyright information. (#413) 2021-08-17 19:52:42 +08:00
Azad Baykara 5c4da16084
[Docs] Fix typo 'metirc' (#411) 2021-08-17 10:35:26 +08:00
Vladislav Sovrasov b54acfd5c4
[Enhance] Avoid unnecessary listdir when building ImageNet. (#396) 2021-08-06 10:38:36 +08:00
Ma Zerun e8822ebaec
[Docs] Fix some bugs in readthedocs pdf build. (#383) 
* Add escape symbols for underscores in formulas.

* Support Chinese characters in pdf output.
 2021-07-31 14:49:36 +08:00
pvys db856df43e
[Fix] Fix ImageNet dataset annotation file parse bug. (#370) 
Co-authored-by: mzr1996 <mzr1996@163.com>
 2021-07-29 10:21:22 +08:00
Ma Zerun 15cd34bbef
[Fix] Use zero as default value of `thrs` in metrics. (#341) 
* Use zero as default value of `thrs` in metrics. And it accepcts a number
instead of float now.

* Fix unit test comment

* Don't pass thrs if no thrs.
 2021-07-18 16:57:21 +08:00
Ma Zerun 76c5d34dcc
[Feature] Support two options in `build_dataloader`. (#349) 
* Support presistent_works in dataloader.

* Use pin_memory by default
 2021-07-14 15:21:49 +08:00
Ma Zerun d04ebc1eb5
[Docs] Add API Reference in the docs (#342) 
* Add API inference in the docs and fix readthedocs config.

* Replace some relative link in docs.

* Format docstring for reStructuredText syntax.

* Fix vit paper link

* Fix docstring of `show_results` function in `BaseClassifier`.
 2021-07-14 15:06:50 +08:00
Ma Zerun 53c0df271f
Fix magnitude_std bug in RandAugment, and update unit tests. (#309) 2021-06-21 11:25:11 +08:00
LXXXXR 2c9e12f850
[Feature] Add an argument `efficientnet_style` to `RandomResizedCrop` and `CenterCrop` (#268) 
* add config for resnest test

* fix config

* add label smoothing

* add memcached

* minor fix

* fix bug

* fix config

* add config

* minor fix

* fix configs

* use EResize

* change interpolation

* add more configs

* add docsting

* add unittest

* remove unnecessary changes

* minor fix

* add more docstring

* fix linting

* refactor

* add resize in crop to ensure crop size is output size

* fix bug and add comments

* fix bug
 2021-05-31 14:10:57 +08:00
LXXXXR bd9411d743
[Bug] Download dataset only on rank 0 (#273) 
* only download dataset on rank 0

* download only on rank 0

* fix bug

* fix error message
 2021-05-29 10:45:58 +08:00
Ma Zerun 09597e5a4c
Add transform `RandomErasing` (#248) 
* Add transform `RandomErasing`.

* Add unittests of `RandomErasing`

* Fix typo in docstring

* Improve docstring and unittests.
 2021-05-19 22:35:26 +08:00
LXXXXR 8c90a879ce
[Fix] Fix magnitude_range in RandAug (#249) 
* add increasing in solarize and posterize

* fix linting

* Revert "add increasing in solarize and posterize"

This reverts commit 128af36e9b.

* revise according to comments
 2021-05-12 15:21:55 +08:00