mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
5,085 Commits
23 Branches
12 Tags
292 MiB
Commit Graph

64 Commits (1c7c7738542b824b65c38801be44e7a29d1383dd)

Author SHA1 Message Date
Wu Chencan 1c7c773854
feat: add fused vision transformer (#3034) 
* add paddleclas_ops csrc

* add fused_vit

* remove "wint4", not support

* add wint4

* add fused_vit README.md

* fit static graph

* fix layernorm dtype

* add static graph infer & performance data

* update weight only scale dtype

* update readme

* update readme
 2024-01-15 13:52:54 +08:00
zhangyubo0722 aae1e9543f
del load pretrained from url for resnet (#2997) 
* del load pretrained from url for resnet

* del load_dygraph_pretrain_from_url

* del load_dygraph_pretrain_from_url

* modify save_load
 2023-10-30 13:44:16 +08:00
cuicheng01 203eba4d6d
support load ssld state1 pretrain (#2988) 2023-09-26 23:48:27 +08:00
zhangyubo0722 ef796960c0 support http pretrained 2023-09-12 17:45:39 +08:00
Bobholamovic b4f10436cf Rename variable 2023-06-26 14:20:38 +08:00
Bobholamovic d6137854e2 Accommodate UAPI 2023-06-26 14:20:38 +08:00
Tingquan Gao 0efda2c75e Revert "refactor: simpfy engine.train()" 
This reverts commit fad5c8e348.
 2023-03-14 16:47:13 +08:00
Tingquan Gao 56e8c5a992 Revert "mv model_saver to __init__()" 
This reverts commit 0d7e595fc7.
 2023-03-14 16:47:13 +08:00
Tingquan Gao 915dde176a Revert "refactor: rm train and eval from engine" 
This reverts commit 5a6fe171a7.
 2023-03-14 16:47:13 +08:00
Tingquan Gao 85e200edb6 Revert "refactor" 
This reverts commit 32593b6375.
 2023-03-14 16:47:13 +08:00
gaotingquan 32593b6375 refactor 2023-03-10 16:56:55 +08:00
gaotingquan 5a6fe171a7 refactor: rm train and eval from engine 2023-03-10 16:56:55 +08:00
gaotingquan 0d7e595fc7 mv model_saver to __init__() 2023-03-10 16:56:55 +08:00
gaotingquan fad5c8e348 refactor: simpfy engine.train() 
1. ModelSaver();
2. _build_ema_model();
3. _init_checkpoints();
4. others.
 2023-03-10 16:56:55 +08:00
HydrogenSulfate 7e12c73e0a polish progressive training code 2023-01-31 21:15:22 +08:00
zhangyubo0722 a5a3b0f567 Delete unnecessary files 2023-01-20 14:08:06 +08:00
root 2a909c306a fix: change to relative import 2022-08-19 11:40:38 +08:00
Yang Nie 436f64ad84 Merge branch 'develop' into ConvNeXt 2022-07-09 21:50:31 +08:00
cuicheng01 8f5fe61540
Merge pull request #1925 from cuicheng01/add_person_demo 
Add person demo
 2022-05-23 09:26:49 +08:00
littletomatodonkey afafb8f41d fix save load 2022-05-17 13:24:24 +00:00
HydrogenSulfate ec80a56e5c fix bug when load dict for optimizer in resume training 2022-05-17 21:04:01 +08:00
HydrogenSulfate f4e400fa3a fix bug when load dict for optimizer in resume training 2022-05-17 21:01:10 +08:00
Yang Nie 098bc1d8b2 Merge remote-tracking branch 'upstream/develop' into ConvNeXt 2022-05-10 21:30:48 +08:00
weishengyu f6923adff8 remove logger.colring 2022-05-10 14:29:20 +08:00
flytocc ed8202236b add EMA code 2022-04-28 00:39:53 +08:00
HydrogenSulfate 3f117428da fix code 2022-04-20 11:08:42 +08:00
HydrogenSulfate 3a1276d315 train_loss_func only used in train mode 2022-04-19 19:54:48 +08:00
HydrogenSulfate 24abea151a support for multi optimizer case 2022-04-19 14:26:42 +08:00
cuicheng01 db46dbd8fe Update save_load.py 2021-07-12 10:35:53 +00:00
littletomatodonkey 2e6dfa4433
fix logger (#840) 
* fix logger
* fix trainer for int64 on windows
 2021-06-15 14:11:50 +08:00
littletomatodonkey 3b4f5f4dfc
add distillation and fix some apis (#810) 
* fix save load and imagenet dataset
* refine trainer
 2021-06-10 16:30:05 +08:00
littletomatodonkey 3881343484
add support for train and eval (#752) 
* add support for train and eval

* rm unsed code

* add support for metric save and load ckp
 2021-05-29 13:52:32 +08:00
Walter decdb51bb0
Merge pull request #742 from cuicheng01/develop_reg 
Add resnet.py in legendary_models
 2021-05-28 11:36:24 +08:00
cuicheng01 31e59dfa1b
add load_dygraph_pretrain_from_url function 2021-05-28 10:55:48 +08:00
littletomatodonkey dd79f81fd7
[WIP]add arch init (#744) 
* polish trainer
 2021-05-27 18:41:44 +08:00
littletomatodonkey e02a35ac45
add quant clas (#621) 
* add quant clas

* fix load init model

* add quant

* add quant doc

* fix export model
 2021-03-01 19:36:55 +08:00
littletomatodonkey 9ebbd78bc9
fix save distillation model (#578) 
* fix save distillation model

* add note
 2021-01-25 20:58:35 +08:00
littletomatodonkey d0ecff1b5a
fix save distillation model (#567) 2021-01-19 18:49:30 +08:00
littletomatodonkey 6abaa0c810
fix dpn (#416) 2020-11-21 17:46:53 +08:00
littletomatodonkey 463980f331
add support for multi cards eval (#413) 
* add support for multi cards eva
 2020-11-20 18:10:06 +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
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 0e0967545a fix load ckp 2020-10-22 06:12:03 +00:00
littletomatodonkey b8a7d186d7 fix optimizer and regularizer 2020-09-15 09:43:19 +00:00
littletomatodonkey b17fbac3dd fix distillation load 2020-09-03 03:24:22 +00:00
littletomatodonkey 927a78872a fix distillation load 2020-09-03 03:22:39 +00:00
littletomatodonkey 6cae5aafa1 add more distillation models 2020-08-29 03:49:27 +00:00
littletomatodonkey 5a15c16581 add dygrapgh load and static load 2020-08-28 09:43:27 +00:00
WuHaobo f5fd4f1fd4 add save and load 2020-06-12 10:55:05 +08:00
WuHaobo 4270c4236a
Merge branch 'master' into master 2020-05-17 16:44:40 +08:00