mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
1,014 Commits
23 Branches
12 Tags
292 MiB
Commit Graph

93 Commits (714a48ea046ec27cc72137dca31536cf2d614f1a)

Author SHA1 Message Date
littletomatodonkey 1e9e8d3fd0
Update ShuffleNetV2_x0_25.yaml 2021-04-16 13:25:49 +08:00
Walter edcef2f292
add quick_start_new_user.md (#680) 
* add quick_start_new_user.md
 2021-04-16 12:42:14 +08:00
gaotingquan 6404d7c582 Del the param to_np 2021-04-16 10:55:31 +08:00
cuicheng01 00f3d48d02
Add quick_start_professional.md (#663) 
* Update quick_start_professional.md
 2021-04-11 22:21:26 +08:00
cuicheng01 23104797a6
Merge pull request #656 from flyseaworld/develop 
add multilabel feature based develop
 2021-04-01 15:52:32 +08:00
huangxu96 525b5e1a0e
Support fp16 training for ResNeXt101_32x4d (#653) 2021-03-31 11:10:19 +08:00
yaohai fee32b555a fix small error 2021-03-30 17:14:25 +08:00
yaohai 5fd7085ddf add multilabel feature 2021-03-30 16:02:32 +08:00
littletomatodonkey d5bdd2db67
Update ResNet50_vd_ssld_random_erasing_finetune.yaml 2021-03-16 13:14:36 +08:00
littletomatodonkey 3b1fad3fa8
Update ResNet50_vd_ssld_finetune.yaml 2021-03-16 11:37:59 +08:00
littletomatodonkey 3388c47e51 fix config, test=document_fix 2021-03-11 17:35:14 +08:00
huangxu96 624f038a6d change the flag of is_distributed. 2021-02-26 09:46:43 +00:00
huangxu96 4e43ec6995 new usage of amp training. (#564) 
* new usage of amp training.

* change the usage of amp and pure fp16 training.

* modified code as reviews
 2021-02-26 09:25:54 +00:00
littletomatodonkey 7af8368016
fix mv3 batch size (#597) 2021-02-15 16:56:56 +08:00
littletomatodonkey ceeb605d9c
fix resnest101 (#604) 2021-02-06 20:32:02 +08:00
jm12138 8cd779be4d
Add RepVGG models (#592) 
* Add RepVGG models

* Update model code

* Rename code

* format code

* add README of RepVGG
 2021-02-01 18:07:25 +08:00
jm12138 6d22322a4f
Update the Configs of ViT and DeiT models (#593) 
* update configs of ViT and DeiT

* update readme of DeiT models

* update readme of DeiT models

* update readme of DeiT models

* update README of ViT models
 2021-02-01 15:21:58 +08:00
Tingquan Gao 3a572f95f1
Add ViT and DeiT (#579) 
* Update the discription about ViT and DeiT

* Fix the error file

* Unified data format
 2021-01-27 16:53:21 +08:00
jm12138 1b89b8a58a
Add the DeiT models (#573) 
* Add the DeiT models

* fix a training bug

* update the model init config

* update the License
 2021-01-22 15:30:55 +08:00
jm12138 747a659891
Add ViT model (#570) 
* Add the ViT model
 2021-01-21 13:05:05 +08:00
littletomatodonkey 0e6fe6f1cf
refine distillation model (#565) 2021-01-19 13:54:27 +08:00
procr da5385c885
support VGG16/19 for kunlun (#561) 2021-01-15 16:24:12 +08:00
littletomatodonkey 21dc73f724
fix quick yaml (#548) 2021-01-07 11:44:58 +08:00
littletomatodonkey b401e10be9
Revert "add amp support for SE_ResNet50_vd (#509)" (#515) 
This reverts commit d51058258b.
 2020-12-25 13:49:00 +08:00
furnace d51058258b
add amp support for SE_ResNet50_vd (#509) 
* add amp support for SE_ResNet50_vd

* updates for data_format
 2020-12-25 13:43:33 +08:00
procr 5b01de1e57
add kunlun HRNet_W18_C_finetune_kunlun.yaml (#508) 2020-12-23 14:25:12 +08:00
Tingquan Gao d860430b55
Fix some description of documentations (#473) 
Fix some description of documentations
 2020-12-14 21:43:45 +08:00
huangxu96 dc3020ab4a
support fp16 training (#435) 
* support fp16 training

* Use compiled training program

* Change timing ips.

* Use dali

* add pure fp16 training

* fix a bug, which will not use fuse pass using pure fp16 training.

* modify code as review

* modify loss, so that it will use different loss when using pure fp16 training.

* remove some fluid API

* add static optimizer.
 2020-12-11 11:04:51 +08:00
QingshuChen 46dfc57e2a
update kunlun epoch num (#445) 2020-12-03 14:06:13 +08:00
QingshuChen 832364e191
support static graph train for kunlun (#441) 2020-12-02 18:36:51 +08:00
littletomatodonkey 07330e0e42
fix resnest typo (#380) 
fix resnest, ghostnet typo
 2020-11-30 12:52:58 +08:00
Tingquan Gao 1975d5b292
Fix name error (#403) 2020-11-18 17:18:46 +08:00
littletomatodonkey 93e4c47909
add resnest101 (#390) 
add resnest101
 2020-11-12 12:13:30 +08:00
littletomatodonkey 7d0f694c7b
unify model and model_name (#386) 
* unify model and model_name

* rm unsed archs fix bug of se_resnext

* fix distillation model for distributed.launch

* fix export model for googlenet
 2020-11-12 00:17:28 +08:00
cuicheng01 30bb0c5aa5
Add InceptionV3 configs in dygraph branch (#373) 
* Add InceptionV3
 2020-11-09 13:46:04 +08:00
littletomatodonkey 4799907e98
Update GoogLeNet.yaml 2020-11-03 13:47:17 +08:00
littletomatodonkey fa6b8f13ac
Update GoogLeNet.yaml 2020-10-30 16:08:10 +08:00
littletomatodonkey bcda9c2b1f
fix squeezenet (#348) 2020-10-30 13:36:08 +08:00
littletomatodonkey 7ef474169d
polish api to Paddle2.0-rc (#346) 
polish codes and docs to adapt Paddle2.0-rc
 2020-10-30 00:20:48 +08:00
littletomatodonkey 806675d226
fix config files (#344) 2020-10-27 17:36:44 +08:00
weishengyu 4cdcd4af74 shufflenet lr cosine -> cosine warmup 2020-10-22 16:11:14 +08:00
weishengyu abd683f968 Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleClas into dygraph 2020-10-22 16:04:55 +08:00
littletomatodonkey 7592654c6b
Merge pull request #318 from littletomatodonkey/dyg/fix_effnet 
fix effnet infer/eval
 2020-10-20 14:41:23 +08:00
littletomatodonkey 58e558fb1c fix effne 2020-10-19 16:23:57 +00:00
gaotingquan 36de6ee3b9 Merge remote-tracking branch 'upstream/dygraph' into dygraph 2020-10-19 16:30:30 +08:00
gaotingquan 27eac3fe63 Fix a bug 2020-10-19 15:33:57 +08:00
littletomatodonkey 73a370fd60 add xception yaml 2020-10-14 05:39:17 +00:00
littletomatodonkey 3ce2db4f83 aad xception_deeplab yaml 2020-10-14 05:39:17 +00:00
weishengyu 44889ba43d Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleClas into dygraph 2020-10-13 11:14:25 +08:00
littletomatodonkey 4d01af9e87 fix reader 2020-10-09 11:47:05 +00:00