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

6 Commits (06f415c28aa8870a1ffcaa5e9e20a2fc928bd4b9)

Author SHA1 Message Date
whcao 3a08db9182
[Feature]Add augments to models/utils (#278) 
* add mytrain.py for test

* test before layers

* test attr in layers

* test classifier

* delete mytrain.py

* add rand_bbox_minmax rand_bbox and cutmix_bbox_and_lam to BaseCutMixLayer

* add mixup_prob to BatchMixupLayer

* add cutmixup

* add cutmixup to __init__

* test classifier with cutmixup

* delete some comments

* set mixup_prob default to 1.0

* add cutmixup to classifier

* use cutmixup

* use cutmixup

* fix bugs

* test cutmixup

* move mixup and cutmix to augment

* inherit from BaseAugment

* add BaseAugment

* inherit from BaseAugment

* rename identity.py

* add @

* build augment

* register module

* rename to augment.py

* delete cutmixup.py

* do not inherit from BaseAugment

* add augments

* use augments in classifier

* prob default to 1.0

* add comments

* use augments

* use augments

* assert sum of augmentation probabilities should equal to 1

* augmentation probabilities equal to 1

* calculate Identity prob

* replace xxx with self.xxx

* add comments

* sync with augments

* for BC-breaking

* delete useless comments in mixup.py
 2021-06-20 09:44:51 +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
whcao 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
whcao 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
whcao 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
ftbabi 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