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

299 Commits (b99bd4fa88c5822583ef131ba010269aba8102a7)
 

Author SHA1 Message Date
WRH b99bd4fa88
Fix bug for CPU training (#286) 
* remove MMDataParallel when using cpu

* support cpu testing

* fix lint
 2021-06-12 22:26:33 +08:00
AllentDan c2f01e0dcd
[Feature] Add torchscript deployment (#279) 
* add torchscript deploy

* fix lint

* add check and delete \
 2021-06-12 21:50:48 +08:00
q.yao dbddde52ef
[Feature] TensorRT test tools. (#284) 
* first commit

* update resnext result

* update docs

* update docstring
 2021-06-12 21:47:10 +08:00
David de la Iglesia Castro e2507cae97
Add mmcls2torchserve (#292) 
* Add mmcls2torchserve

* Update docs
 2021-06-12 21:45:45 +08:00
whcao 5e1a02103f
[Feature]Delete comments (#298) 
* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* delete comments
 2021-06-12 21:45:22 +08:00
Ma Zerun 84a939f858
Refactor LabelSmoothLoss (#285) 
* Refector label smooth loss, now support mode `original`, `classy_vision`
and `multi_label`.

* Add unittests for label smooth loss.

* Improve docstring of LSR
 2021-06-12 21:32:18 +08:00
LXXXXR 6de635a81c
[Bug] Missing test data when num_imgs can not be evenly divided by num_gpus (#299) 
* fix bug in test

* remove unneccesary code
 2021-06-11 15:53:23 +08:00
Miao Zheng 4ca21c7d03
[WIP] Refactoring weights initialization (#270) 
* [WIP] Refactoring weights initialization

* fix lint and constant init cfg

* fix pretrained bug

* fix typo

* fix isort

* revise model utils
 2021-06-10 10:54:34 +08:00
LXXXXR 5066e32306
dump config before training (#282) 2021-06-04 16:26:13 +08:00
Ma Zerun 9f7168e770
Add RegNetX configs (#269) 
* Add RegNetX configs

* Fix typo in RegNet readme.

* Use comment to mark tag.
 2021-06-04 14:29:13 +08:00
Ma Zerun b95caca0d5
Redirect model_zoo.md and format Chinese documents. (#290) 
* Redirect model_zoo.md in Chinese Readme to English ver.

* Format Chinese documents.
 2021-06-03 16:49:53 +08:00
LXXXXR c68bf9f2ba
fix resnetv1d configs and update ckpts (#288) 2021-06-03 16:30:29 +08:00
LXXXXR 27a49a9646
bump version to v0.12.0 (#287) 2021-06-03 11:42:34 +08:00
LXXXXR df3d2d47f0
update resnext ckpts (#283) 2021-06-01 14:57:46 +08:00
LXXXXR 5ff158cec9
[Bug] Fix Cifar color channel (#280) 
* fix bug

* updatedoc accordingly
 2021-05-31 14:15:22 +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
Mingqiang Ning 9a66113d20
add attribute 'test' in dict 'data' (#264) 
* add attribute 'test' in dict 'data'

* Update lenet5_mnist.py

 delete spaces around '='.

* init

* Delete custom directory
 2021-05-31 10:19:27 +08:00
Ma Zerun 4524327a4a
[Docs] Fix typo, improve and add Chinese translation of `data_pipeline.md` and `new_modules.md` (#265) 
* Improve docs, including `new_modules.md` and `data_pipeline.md`

* Add Chinese docs `new_modules.md` and `data_pipeline.md`
 2021-05-29 10:48:31 +08:00
LXXXXR b23b319f56
fix version (#276) 2021-05-29 10:47:16 +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 a06827bc08
Build chinese translation in readthedocs (#267) 
* change document layout

* Add Chinese docs build file

* Add switch language option
 2021-05-29 10:00:37 +08:00
LXXXXR 98b6c4afa4
update cifar config (#275) 2021-05-27 15:20:25 +08:00
Yinhao Li b67a11c548
Fix kwargss to kwargs. (#274) 2021-05-26 19:27:30 +08:00
LXXXXR dac090162d
Bump version to v0.11.1 (#256) 
* bump version to v0.11.1

* minor fix

* minor fix

* minor fix

* minor fix
 2021-05-21 16:36:08 +08:00
Y. Xiong 82e3937174
[Fix] Only allow directory operation when rank==0 when testing (#258) 
* only allow dir operation when rank==0

* move check dir to multi_gpu_test
 2021-05-21 14:04:46 +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 ace09510f7
[Bug]Fix typo (#255) 
* fix typo

* rerun ci
 2021-05-17 10:42:31 +08:00
LXXXXR dc296f64c6
[Fix] Fix multi-node test tmp dir (#251) 
* fix multi-node test tmp dir

* fix mmcv version
 2021-05-16 21:53:13 +08:00
Wenwei Zhang 5ee08767f2
inherits mmcv registry (#252) 2021-05-14 23:36:56 +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
LXXXXR f415c49bc3
fix MANIFEST.in (#250) 2021-05-12 15:04:58 +08:00
mzr1996 9e93feabac
[Docs] Fix error in new_dataset.md and add Chinese translation of finture.md, new_dataset.md (#243) 
* Fix error in new_dataset.md

* Add Chinese Translation of finture.md, new_dataset.md
 2021-05-10 17:17:37 +08:00
mzr1996 a3b8d6015d
[Feature] Add RandAUG magnitude noise (#240) 
* Add paramater magnitude_std in RandAugment to allow randomly movement of magnitude_value

* Add unittest for magnitude_std

* Improve docstring of magnitude_std
 2021-05-10 17:13:41 +08:00
Y. Xiong 22b40696d6
add tempdir check (#242) 2021-05-10 17:12:43 +08:00
Forsaken 0a92a81198
Update analyze_results.py (#237) 
correct spelling mistake(sucess->success)
 2021-05-10 15:04:08 +08:00
RangiLyu 6a50a2864b
fix typo in unit test (#238) 2021-05-10 15:03:39 +08:00
mzr1996 8128900a12
GlabelAveragePooling support 1d, 2d and 3d by param, and add neck test (#236) 
* GlabelAveragePooling support 1d, 2d and 3d by param, and add neck test

* Imporve neck test

* Change 'mode' attribute in GAP to 'dim', and add docstring
 2021-05-10 15:00:50 +08:00
whcao b30f79ea4c
[Feature]Modify Parameters Passing in models.heads (#239) 
* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* set cal_acc in ClsHead defaults to False

* set cal_acc defaults to False

* use *args, **kwargs instead

* change bs16 to 3 in test_image_classifier_vit

* fix some comments

* change cal_acc=True

* test LinearClsHead
 2021-05-10 14:56:55 +08:00
LXXXXR 37167158e7
bump version to v0.11.0 (#233) 2021-05-01 22:26:39 +08:00
LXXXXR 761c95925d
support mmcli (#232) 2021-05-01 22:24:16 +08:00
QingChuanWS f970a36898
update pytorch2onnx.md table (#229) 2021-04-30 17:18:06 +08:00
whcao 3be95b99c2
[Feature]Modify modelzoo readme (#230) 
* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* add imagenet_bs4096_AdamW.py

* delete 2 lines of comments

* change bs to 64

* fix bug

* add vit to model_zoo.md

* rename
 2021-04-29 15:18:55 +08:00
whcao 16947f1239
[Bug]Fix weight decay (#227) 
* add imagenet bs 4096

* add vit_base_patch16_224_finetune

* add vit_base_patch16_224_pretrain

* add vit_base_patch16_384_finetune

* add vit_base_patch16_384_finetune

* add vit_b_p16_224_finetune_imagenet

* add vit_b_p16_224_pretrain_imagenet

* add vit_b_p16_384_finetune_imagenet

* add vit

* add vit

* add vit head

* vit unitest

* keep up with ClsHead

* test vit

* add flag to determiine whether to calculate acc during training

* Changes related to mmcv1.3.0

* change checkpoint saving interval to 10

* add label smooth

* default_runtime.py recovery

* docformatter

* docformatter

* delete 2 lines of comments

* delete configs/_base_/schedules/imagenet_bs4096.py

* add configs/_base_/schedules/imagenet_bs2048_AdamW.py

* rename imagenet_bs4096.py to imagenet_bs2048_AdamW.py

* add AutoAugment

* fix weight decay in vit

* change eval interval to 10

* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* delete @torch.jit.ignore

* change eval interval back to 1

* add some comments to imagenet_bs2048_AdamW

* add some comments
 2021-04-28 17:16:43 +08:00
LXXXXR 5fb9ced5f9
[Docs] Change tag into comment (#226) 
* change tags

* remove modelzoo_statistics
 2021-04-28 17:08:57 +08:00
LXXXXR a604cd97ef
[Feature] Adding PWC metafile (#225) 
* add yml

* fix VGG

* minor fix

* add model zoo

* add bs and epoch

* revised according to comments

* revised according to comments

* revised according to comments
 2021-04-28 17:07:26 +08:00
mzr1996 3d87474c71
Add Chinese Readme and docs (#221) 
* Add Citation in README

Add Citation and mmgeneration in README

* Merge inference and test section in getting_start.md and other small chagne.

* Fix code type in install.md

* Add Chinese Readme

* README and docs improvement.
 2021-04-26 13:58:18 +08:00
QingChuanWS 01d2849b76
[Feature]: add onnxruntime test tool (#212) 
* [draft] add onnxruntime accuruacy verification

* fix a bug

* update code

* fix lint

* fix lint

* update code and doc

* update doc

* update code

* update code

* updata doc and updata code

* update doc and fix some bug

* update doc

* update doc

* update doc

* update doc

* update doc

* update doc

* fix bug

* update doc

* update code

* move CUDAExecutionProvider to first place

* update resnext accuracy

* update doc

Co-authored-by: maningsheng <maningsheng@sensetime.com>
 2021-04-26 13:57:08 +08:00
WRH 9be435846c
Support training on CPU (#219) 
* draft

* add parameter for training tools

* Update .pre-commit-config.yaml
 2021-04-26 13:56:45 +08:00
LXXXXR d72d233f9b
fix resnext resize (#222) 2021-04-25 16:26:34 +08:00
whcao 759aa92437
[Bug]add cutmix_prob to config (#220) 
* add cutmix_prob to config

* empty
 2021-04-21 21:57:09 +08:00