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
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
31a6a362ba
Add some vit configs ( #217 )
...
* add vit_base_patch32_384_finetune.py
* add vit_base_patch32_384_finetune_imagenet.py to vision_transformer
* add vit_large_patch16_384_finetune.py to models
* add vit_large_patch16_384_finetune_imagenet.py to vision_transformer
* add vit_large_patch32_384_finetune to models
* add vit_large_patch32_384_finetune_imagenet to vision_transformer
* add vit_large_patch16_224_finetune.py to models
* add vit_large_patch16_224_finetune_imagenet.py to vision_transformer
* delete some useless comments
2021-04-20 11:32:20 +08:00
affb39fe07
[Feature]Add Vit ( #214 )
...
* 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 helpers.py
* test vit hybrid backbone
* fix HybridEmbed
* use to_2tuple instead
2021-04-16 19:22:41 +08:00
7d618e6606
[Fix] Fix version ( #209 )
...
* fix version
* add projects in openmmlab
* minor fix
* empty
* add mmocr
* empty
* empty
* fix linting
2021-04-16 19:07:17 +08:00
3affc481c8
[Fix] check for CLASSES in checkpoint meta ( #207 )
...
- check for CLASSES in checkpoint meta when key meta does not exists
2021-04-15 22:19:23 +08:00
1cde6f6e65
[Feature] Add cutmix option ( #198 )
...
* Add cutmix option
* fix code style
* add some annotations
* add annotation about custom_hooks
* check constraint of alpha > 0
* add test cutmix
* fix code style
* add cutmix to configs/models
* add cutmix to configs/resnet
* flake8
* empty
2021-04-14 21:27:42 +08:00
b7b520881f
Update CONTRIBUTING.md according to mmcv ( #210 )
...
* Update CONTRIBUTING.md according to mmcv
* Docstring formatting by docformatter
* Update openmmlab website.
2021-04-14 21:22:37 +08:00
af83e981ac
[Bug]Fix label smooth bug ( #203 )
...
* add convert_to_one_hot
* add test_label_smooth_loss
* add my label_smooth_loss
* fix CELoss bug
* test new label smooth loss
* LabelSmoothLoss downward compatibility
* add some comments
* remove the old version of LabelSmoothLoss
* add some comments
* add some comments
* add some comments
* add label smooth to config
2021-04-13 13:53:56 +08:00
dcf61173f6
[Feature]Add cal_acc to cls_head.py ( #206 )
...
* add cal_acc to cls_head.py
* test ClsHead with cal_acc
* 4 spaces indentation
2021-04-13 13:52:14 +08:00
5195932952
[Feature] Support random augmentation ( #201 )
...
* support random augmentation
* minor fix on posterize
* minor fix on posterize
* minor fix on cutout
* minor fix on cutout
* fix bug in solarize add
* revised according to comments
2021-04-09 14:02:50 +08:00
4d1fb1a662
[Feature] ColorJitter and Lighting ( #190 )
...
* add configs
* remove config
* add color jitter and lighting
* revised according to comments
2021-04-02 19:23:39 +08:00
1f6549eeee
bump version to 0.10.0 ( #194 )
2021-04-01 10:39:18 +08:00
93cd960466
[Feature] Support AutoAug, AutoContrast, Equalize, Contrast, Brightness and Sharpness ( #179 )
...
* add AutoContrast, Equalize, Contrast, Brightness and Sharpness pipelines
* add ImageNetPolicy
* add configs
* add unittest
* remove config
* rerun CI
* rerun CI
* [Fix] Update pip install mmcv command in ci (#187 )
* update pip install mmcv command in ci
* update pip install mmcv command in ci
* fix ci
* fix ci
2021-03-30 15:38:55 +08:00
b507fc207b
[Fix] Use MMCV's EvalHook in MMClassification ( #182 )
...
* use eval_hook in mmcv
* minor fix
2021-03-25 17:38:51 +08:00
e76c5a368d
[Feature] Support fp16 training ( #178 )
...
* change mmcls fp16 to mmcv hook
* support fp16
* clean unnessary stuff
2021-03-17 15:53:55 +08:00
f3b9380cbc
[Feature] Support solarize and posterize pipelines ( #172 )
...
* support Solarize and Posterize
* revised according to comments
* fix conflicts
2021-03-09 19:45:13 +08:00
9614787fc4
[Feature] Add color pipeline ( #171 )
...
* add ColorTransform pipeline
* fix docstring
* minor change
* revised according to comments
2021-03-09 19:28:50 +08:00
c8033ece8e
add invert pipeline ( #168 )
2021-03-02 16:46:57 +08:00
b1fa298a66
add Rotate pipeline ( #167 )
2021-03-01 21:49:07 +08:00
7ca0ca271f
Bump version to 0.9.0 ( #166 )
...
* update docs for version 0.9.0
* add missing #153
2021-03-01 20:14:53 +08:00
bc50a7927b
reslove conflicts ( #165 )
2021-02-26 11:48:13 +08:00
8c11c01fdb
[Feature] Add shear pipeline ( #163 )
...
* half-done auto_augmentation
* remove auto_augcode and support shear pipeline
* fix typo
* fix typo
* use a non-square toy data instead
2021-02-25 16:00:46 +08:00
fb11a23cfe
Show results in test api ( #162 )
...
* Initial support show in single_gpu_test
* Add result_show
* Add ori_filename meta_key
* test ori_filename
* Add show, show-dir, show-options
2021-02-25 16:00:22 +08:00
bdd6b01ae7
[Feature] Add "mixup" from Bag of Tricks ( #160 )
...
* Add mixup option
* Modify the structure of mixup and add configs
* Clean configs
* Add test for mixup and SoftCrossEntropyLoss
* Add simple test for ImageClassifier
* Fix bug in test_losses.py
* Add assertion in CrossEntropyLoss
2021-02-25 14:06:58 +08:00
ddc2a14177
[Feature] Add --eval-options in test.py ( #158 )
...
* add --eval-options in test.py
* fix typo
* revise according to commnets
2021-02-05 17:46:43 +08:00
7f49632d7c
Bump version to 0.8.0 ( #156 )
...
* update docs to bump version
* minor change
* revise acording to comments
2021-01-31 17:50:40 +08:00
a225cb6bdb
fix img_metas bug ( #152 )
2021-01-26 11:24:08 +08:00
3e5a9513be
[Bug] Fix bug in Collect ( #149 )
...
* fix bug in Collect
* add metakeys
2021-01-25 20:29:28 +08:00
fc82c31b2f
fix RandomCrop and RandomResizedCrop ( #151 )
2021-01-25 20:28:16 +08:00
07bb15e5fd
[Feature] Add heads and config for multilabel task ( #145 )
...
* resolve conflicts
add heads and config for multilabel tasks
* minor change
* remove evaluating mAP in head
* add baseline config
* add configs
* reserve only one config
* minor change
* fix minor bug
* minor change
* minor change
* add unittests and fix docstrings
2021-01-25 18:10:14 +08:00
13c1210741
[Feature] Add thrs in eval_metrics ( #146 )
...
* support thr
* replace thrs with thr
* fix docstring
* minor change
* revise according to comments
* revised according to comments
* revise according to comments
* rewrite basedataset.evaluate to avoid duplicate calculation
* minor change
* change thr to thrs
* add more unit test
2021-01-25 17:54:22 +08:00
8e990b5654
[Feature] Support support and class-wise evaluation results ( #143 )
...
* support support, support class-wise evaluation results and move eval_metrics.py
* Fix docstring
* change average to be non-optional
* revise according to comments
* add more unittest
2021-01-19 16:42:16 +08:00
b98b317012
fix bug in vgg weight_init ( #140 )
2021-01-15 10:23:11 +08:00
63f38988eb
[Fix] Fix optional issues in docstring ( #138 )
...
* fix optional issue in docstring
* revised according to comments
* add optional
2021-01-14 11:09:08 +08:00
6916f33d56
[Feature] Add asymmetric loss for multilabel task ( #132 )
...
* add asymmetric loss
* minor change
* fix docstring
* do not apply sum over classes and fix docstring
* fix docstring
* fix weight shape
* fix weight shape
* add reference
* fix linkting issue
Co-authored-by: Y. Xiong <xiongyuxy@gmail.com>
2021-01-11 11:22:22 +08:00
c07e60dd7d
[Feature] Support PASCAL VOC 2007 dataset for multilabel task ( #134 )
...
* support voc
* minor change
2021-01-11 11:08:59 +08:00
194ab7efda
[Feature] Add bce loss for multilabel task ( #130 )
...
* add bce loss for multilabel task
* minor change
* apply class wise sum
* fix docstring
* do not apply sum over classes and fix docstring
* fix docstring
* fix weight shape
* fix weight shape
* fix docstring
* fix linting issue
Co-authored-by: Y. Xiong <xiongyuxy@gmail.com>
2021-01-11 11:05:24 +08:00
9578bfa0f1
[Feature] Add focal loss for multilabel task ( #131 )
...
* add focal loss
* apply class wise sum
* fix doctring
* do not apply sum over classes and fix docstring
* fix docstring
* fix weight shape
* fix weight shape
2021-01-08 20:44:23 +08:00
1df10beaa1
Add evaluation metrics for multilabel task ( #123 )
...
* add mean_ap
* add difficult_examples in mAP to support dataset without difficult_examples
* fix docstring
* add CP,CR,CF1,OP,OR,OF1 as multilabel metrics
* fix docstring
* temporary solution to ci until new version of mmcv is avaliable (#127 )
* temporary solution to ci until new version of mmcv is avaliable
* temporary solution to ci until new version of mmcv is avaliable
* add mean_ap
* add difficult_examples in mAP to support dataset without difficult_examples
* fix docstring
* add CP,CR,CF1,OP,OR,OF1 as multilabel metrics
* fix docstring
* Swap -1 and 0 for labels
* Revised according to comments
* Revised according to comments
* Revised according to comments
* Revert "Revised according to comments"
It is suggested that we should not include paper from arxiv.
This reverts commit 48a781cd6a6d3b0f1a7b120ecda884
2021-01-04 12:25:33 +08:00
d835cd005a
Bump version to 0.7.0 ( #129 )
...
* add change log and unable MD024 in pre-commit hook
* fix readme and modify version
* Revised according to comments
2020-12-31 16:41:45 +08:00
4203b94643
fix bug in eval_metrics ( #122 )
2020-12-23 16:20:47 +08:00
6331eb3e2f
[Bug] Fix bug in collect_results ( #114 )
...
* fix bug in collect results
* fix compatibility issue in build.yml
* fix compatibility issue in build.yml
* revert changes in ci
* add comments
2020-12-18 17:00:47 +08:00
b1e91f256b
fix bug in recall and precision ( #112 )
2020-12-09 16:27:42 +08:00
92438da12a
fix bug ( #108 )
2020-12-04 11:41:49 +08:00
6f7698cb7c
Update accuracy.py ( #104 )
...
Co-authored-by: Ülkü Tuncer Küçüktaş <UlkuTuncerKucuktas@users.noreply.github.com>
2020-12-01 14:25:18 +08:00
5de2d2c0e9
Change to use mmcv.utils.collect_env to avoid duplicate codes ( #103 )
2020-12-01 14:24:08 +08:00
44bbc71e14
Fix bug and optimize MNIST config ( #98 )
...
* add simple_test to ClsHead
* optimize lenet training config
* recover path setting
2020-11-26 15:27:04 +08:00
c0e7512969
support options to override configs in inference.py ( #96 )
2020-11-25 16:14:01 +08:00
21fd5019fb
add macro-averaged precision,recall,f1 options in evaluation ( #93 )
...
* add macro-averaged precision,recall,f1 options in evaluation
* remove unnecessary comments
* Revise according to comments
* Revise according to comments
2020-11-25 16:13:54 +08:00
149ee3a30d
support img input as ndarray in inference.py ( #87 )
...
* support img input as ndarray
* revise according to comments
2020-11-19 18:58:25 +08:00
7636409b3b
add get_class in base_dataset ( #85 )
...
* modify base_dataset
* revise according to the comments
2020-11-12 14:22:02 +08:00
909a6b9c3f
Add get_cat_ids in BaseDataset ( #72 )
...
* visualize results on image demo
* add get_cat_ids in BaseDataset
2020-10-26 14:04:10 +08:00
784987fe9f
Fix slurm evaluation error during training ( #69 )
...
* visualize results on image demo
* set round_up to True during test
2020-10-20 15:04:39 +08:00
df2189c6f6
Add missing CLASSES argument to dataset wrappers ( #66 )
...
* Add missing classes in dataset wrappers
* Update tests
2020-10-15 21:25:53 +08:00
4f4f2957ef
Use build_runner ( #54 )
...
* Use build_runner in train api
* Support iter in eval_hook
* Add runner section
* Add test_eval_hook
* Pin mmcv version in install docs
* Replace max_iters with max_epochs
* Set by_epoch=True as default
* Remove trailing space
* Replace DeprecationWarning with UserWarning
* pre-commit
* Fix tests
2020-10-15 21:12:50 +08:00
d369645e23
bump version to 0.6.0 ( #62 )
...
* fix lint
* fix version path type
* del short_version
* setup: del ops; add python3.8
* del useless requirements
* setup: remove extra_requirements
* setup: totally remove build_requests
* setup: change to valid email
2020-10-11 00:12:04 +08:00
24fd4fb627
Visualize results on image demo ( #58 )
...
* visualize results on image demo
* add matplotlib in requirements
2020-10-10 16:33:27 +08:00
9547e7b7a5
Add model inference ( #16 )
...
* add model inference on single image
* rm --eval
* revise doc
* add inference tool and demo
* fix linting
* rename inference_image to inference_model
* infer pred_label and pred_score
* fix linting
* add docstr for inference
* add remove_keys
* add doc for inference
* dump results rather than outputs
* add class_names
* add related infer scripts
* add demo image and the first part of colab tutorial
* conduct evaluation in dataset
* return lst in simple_test
* compuate topk accuracy with numpy
* return outputs in test api
* merge inference and evaluation tool
* fix typo
* rm gt_labels in test conifg
* get gt_labels during evaluation
* sperate the ipython notebook to another PR
* return tensor for onnx_export
* detach var in simple_test
* rm inference script
* rm inference script
* construct data dict to replace LoadImage
* print first predicted result if args.out is None
* modify test_pipeline in inference
* refactor class_names of imagenet
* set class_to_idx as a property in base dataset
* output pred_class during inference
* remove unused docstr
2020-09-30 19:00:20 +08:00
bc1b08ba41
Add VGG and pretained models ( #27 )
...
* add vgg
* add vgg model coversion tool
* fix out_indices and docstr
* add vgg models in configs
* add params, flops and accuracy in docs
* add pretrained models url
* use ConvModule and refine var names
* update vgg conversion tool
* modify bn config
* add docs for arch_setting
* add unit test for vgg
* rm debug code
* update vgg pretrained models
2020-09-29 17:49:42 +08:00
99115fddbc
Add albumentations ( #45 )
...
* Add Albu transform
* pre-commit
* Create optional.txt
* Update requirements.txt
* Update transforms.py
2020-09-22 17:35:39 +08:00
8d3acce307
Add ResNeSt ( #25 )
...
* Add ResNeSt
* fixed test
* refactor
* add ResNeSt base
* update modelzoo
* update modelzoo
* Add S-200,S269 _base_
2020-09-22 10:41:51 +08:00
fef5202257
Fix crash in CenterCrop transform when image is greyscale ( #40 )
2020-08-31 00:04:39 +08:00
7af9419ffa
Fix init_weights in 'shufflenet_v2.py'. ( #29 )
...
* fix init_weights in shufflenetv2
* fix doc
* fix doc
Co-authored-by: lixiaojie <lixiaojie@sensetime.com>
2020-08-13 09:49:41 +08:00
408d92bcbe
revise docstr of alexnet to correct input_size ( #26 )
2020-08-12 16:14:19 +08:00
c905decddf
Resize according to short edge ( #22 )
...
* resize according to short edge
* revise doc for resize
* fix unitest for resize
* resize short_edge when second value of size is -1
* rename short_edge to short_side
2020-08-11 16:04:45 +08:00
a0c814fecd
add doc for backend
2020-08-05 15:35:40 +08:00
34efbc8a9d
add pil backend for resize
2020-08-03 12:52:35 +08:00
557a364d25
replace urlretrieve with urlopen ( #13 )
2020-07-27 22:20:03 +08:00
0fb9b2f140
Update readme ( #3 )
...
* add badges and license
* minor format
2020-07-13 12:55:34 +08:00
9a661ef981
Add ResNet_CIFAR
2020-07-12 00:06:56 +08:00
e29882c8af
fix old register
2020-07-12 00:06:56 +08:00
c1d0090700
Change the init_weight for shufflenet models
2020-07-12 00:06:56 +08:00
6968ad5b3b
Add RandomFlip
2020-07-12 00:06:56 +08:00
45812e87bd
add weighted_loss
2020-07-12 00:06:55 +08:00
1d5f3d8c24
update shufflenet_v1
2020-07-12 00:06:55 +08:00
f6260b33bf
Add RandomCrop, RandomResizedCrop, RandomGrayscale, impad
2020-07-12 00:06:55 +08:00
8995e16834
Add AlexNet and LeNet5
2020-07-12 00:06:54 +08:00
fbc68bf266
Add classifiers, heads, necks and losses
2020-07-07 19:32:06 +08:00
910d13330a
Add Resize and CenterCrop
2020-07-07 17:07:58 +08:00
17092d8be4
Fix the mid_channels of SEResNeXt
2020-07-07 11:25:48 +08:00
eb24a94b68
add mobilenetv2 convert code
2020-07-05 21:59:22 +08:00
f45dc9541b
use mmcv.ProgressBar to replace tqdm
2020-07-05 21:57:42 +08:00
046aa5c003
add shufflenet_v2 convert code
2020-07-03 19:21:18 +08:00
ba789da5c8
Add commonly used datasets
2020-07-01 16:09:06 +08:00
91a43c5bac
Add RegNet
2020-07-01 14:21:45 +08:00
03b75789c6
Dev mobilenetv3
2020-06-30 15:50:36 +08:00
02e11cc1f3
Refactoring for ResNet family
2020-06-25 11:57:50 +08:00
50208498dd
Update mobilenetv2
2020-06-22 19:40:31 +08:00
29e17ab326
Dev se resnext
2020-06-19 11:45:42 +08:00
f729a60f87
Dev se resnet
2020-06-17 14:20:20 +08:00
c168aa786e
Merge branch 'fix/resnet_zero_init_residual' into 'master'
...
Set default zero_init_residual of ResNet to True
See merge request open-mmlab/mmclassification!22
2020-06-16 22:09:48 +08:00
deee5d61d7
add mobilenetv2
2020-06-16 14:37:03 +08:00
800ace3137
set default zero_init_residual to True
2020-06-16 11:36:54 +08:00
fcb1ad80e4
merge master
2020-06-16 00:49:55 +08:00
66e9bb017d
fix unit test
2020-06-16 00:03:45 +08:00
8060e0f620
merge master
2020-06-15 20:54:52 +08:00
1ce116a898
Merge branch 'master' of gitlab.sz.sensetime.com:open-mmlab/mmclassification into dev_shufflenetv1
2020-06-15 20:52:27 +08:00
edceab13e3
modify self.layers
2020-06-15 20:52:17 +08:00
5662daeea8
Merge branch 'dev_shufflenetv1' into 'master'
...
add shufflenetv1
See merge request open-mmlab/mmclassification!10
2020-06-15 20:49:44 +08:00
QingChuanWS
WRH
whcao
LXXXXR
agim-a
mzr1996
David de la Iglesia Castro
ftbabi
Ülkü Tuncer Küçüktaş
Lei Yang
Y. Xiong
Jerry Jiarui XU
anthracene
Xiaojie Li
Kai Chen
yanglei
lixiaojie
chenkai
louzan
yangmingmin
qianchen