mirrors/PaddleClas
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleClas.git synced 2025-06-03 21:55:06 +08:00
Code Issues Projects Releases Wiki Activity
5,063 Commits 23 Branches 12 Tags
Commit Graph

295 Commits

Author SHA1 Message Date
zhenming lin
98935e0bb7
Add ML-Decoder Support (#2957) 
* 添加ML-Decoder，并使其可以在Arch作用域下控制

* 添加MultiLabelAsymmetricLoss

* 添加MultiLabelMAP评价方式，并避免其在回合内计算，每回合计算一次，节约时间

* 添加COCO2017数据集格式转换脚本

* 添加OneCycleLR学习率调度策略

* 添加ResNet50_ml_decoder

* 添加ResNet_ml_decoder

* 添加ResNet_ml_decoder

* 添加ResNet_ml_decoder preprocess

* 添加ResNet_ml_decoder

* 添加ResNet_ml_decoder

* 直接从model中拉class_num参数

* fix message error

* fix message error

* 给出基于inference model预测的文档

* 融合cutout使其具有随机生成填充值的能力

* 更正变量名称

* 更新configs

* 更新README

* fix bugs

* fix bugs

* update

* update

* update
 2023-09-08 16:17:35 +08:00
zhangyubo0722
d7a7d3e5e1
fix topk bug (#2945) 2023-09-01 19:28:17 +08:00
zhangyubo0722
74a33b7f50
fix gbk (#2941) 2023-09-01 17:49:33 +08:00
wuyefeilin
83adff2acc
add dataset alias for PaddleX (#2893) 2023-08-02 10:41:25 +08:00
cuicheng01
4da6f35bf2 support infer nested directory images 2023-06-29 19:43:40 +08:00
gaotingquan
377950865c getargspec -> getfullargspec 
getargspec dont support param annotations
 2023-05-17 15:19:13 +08:00
Yang Nie
deb8e98779 rename v2 to V2 2023-04-19 21:21:06 +08:00
Yang Nie
be6a22be18 add MobileViTv2 2023-04-19 21:21:06 +08:00
gaotingquan
31ea33c884 revert the cutmix, mixup, fmix fixes 
because this change(commit: df31d808fcd13ef7840e6d7682150ddc5eab1628) will cause other issues, such as a change in the value of QA monitoring, so revert temporary.
 2023-04-12 20:55:38 +08:00
Yang Nie
400de7844f update RandAugmentV3 2023-04-06 15:33:30 +08:00
Yang Nie
ee40e1fc76 bugfix: make the epoch in MultiScaleSampler self-incrementing 2023-04-06 15:33:30 +08:00
Yang Nie
df31d808fc bugfix: MixupOperator, CutmixOperator, FmixOperator 2023-04-06 15:33:30 +08:00
Yang Nie
541326eaf0 bugfix: DecodeImage 2023-04-06 15:33:30 +08:00
Yang Nie
03bd4e4419 add use_log_aspect for RandCropImage 2023-04-04 20:37:22 +08:00
Yang Nie
3b8b39644f change the default interpolation of pil from NEAREST to BILINEAR (same to cv2 backend) 2023-04-04 20:37:22 +08:00
Yang Nie
a2052232e6 add support for CvT_21_244, CvT_13_384, CvT_21_384 and CvT_W24_384 2023-04-04 18:44:44 +08:00
Yang Nie
d7a1127559 add CvT 2023-04-04 18:44:44 +08:00
Tingquan Gao
5d06a88a36 Revert "refactor: simplify engine" 
This reverts commit 376d83d46e54a03e96477d707a9d6addb8fee756.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
e7e4f68b5c Revert "refactor: build_train_func & build_eval_func" 
This reverts commit 6bed0f5707e58dc02d71d3ea335a55cd1a454264.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
f2fc43baeb Revert "refactor: mv all dataloaders to engine.dataloader_dict" 
This reverts commit 284e2a67564d4b1f5f4a9c04c7c1ab0e8d3ada75.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
a1e840e0da Revert "refactor: iter_per_epoch -> max_iter" 
This reverts commit a38e42f644fcba8b60a9672762211b6f7054b290.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
f42719afbb Revert "replace the arg engine with config" 
This reverts commit f525cea006c66b11e6fee69b2088d0adc08ca57f.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
7243f1429b Revert "rm codes for compatibility with old version" 
This reverts commit 6e77bd6cd5f154d448b0c86e29ff1179b30f2755.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
339be96ef5 Revert "refactor" 
This reverts commit 187f38ebdd63b0adae2abf72038dc4fb4fe4125c.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
85e200edb6 Revert "refactor" 
This reverts commit 32593b63751b922e17b59384ed64654e6fcef42d.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
03795249c1 Revert "revert for running" 
This reverts commit d3374e897e162053d93a20c21142135c3e7ee11c.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
8002ccf4b6 Revert "support ShiTu" 
This reverts commit 9beb154bc3d082f521b05df49d538f93d5e5c0d4.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
8adb5f4a32 Revert "debug for dali" 
This reverts commit c641fb3c516891e97375f34df653f252c4e008ca.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
8580242724 Revert "debug" 
This reverts commit a41a5bcb4d055e88b6a83b76a4607651656cdf51.
 2023-03-14 16:47:13 +08:00
Tingquan Gao
753270abcf Revert "debug" 
This reverts commit afc9b4c69417d79c65c5b050311ad3c5602d9258.
 2023-03-14 16:47:13 +08:00
gaotingquan
afc9b4c694 debug 2023-03-10 16:56:55 +08:00
gaotingquan
a41a5bcb4d debug 2023-03-10 16:56:55 +08:00
gaotingquan
c641fb3c51 debug for dali 2023-03-10 16:56:55 +08:00
gaotingquan
9beb154bc3 support ShiTu 2023-03-10 16:56:55 +08:00
gaotingquan
d3374e897e revert for running 2023-03-10 16:56:55 +08:00
gaotingquan
32593b6375 refactor 2023-03-10 16:56:55 +08:00
gaotingquan
187f38ebdd refactor 
1. rm Global.eval_mode
2. add Global.task
3. mv type_name to ppcls.utils
4. build dataloader, loss, metric by mode
 2023-03-10 16:56:55 +08:00
gaotingquan
6e77bd6cd5 rm codes for compatibility with old version 2023-03-10 16:56:55 +08:00
gaotingquan
f525cea006 replace the arg engine with config 2023-03-10 16:56:55 +08:00
gaotingquan
a38e42f644 refactor: iter_per_epoch -> max_iter 2023-03-10 16:56:55 +08:00
gaotingquan
284e2a6756 refactor: mv all dataloaders to engine.dataloader_dict 2023-03-10 16:56:55 +08:00
gaotingquan
6bed0f5707 refactor: build_train_func & build_eval_func 
1. rm engine.device and use paddle.device.get_device() instead;
2. mv some code to build_train_func or build_eval_func to simpfy engine.
 2023-03-10 16:56:55 +08:00
gaotingquan
376d83d46e refactor: simplify engine 2023-03-10 16:56:55 +08:00
tianyi1997
7c3bb2754b Update files according to reviews 
https://github.com/PaddlePaddle/PaddleClas/pull/2633
 2023-02-28 15:01:21 +08:00
tianyi1997
21e76d08b6 Modify codes based on reviews 2023-02-28 15:01:21 +08:00
tianyi1997
1070d9bec0 Create dataloader for MetaBIN 2023-02-28 15:01:21 +08:00
zh-hike
23b011206a fix randomapply 2023-02-15 11:17:18 +08:00
zhangyubo0722
79cbd7350a Aesthetic 2023-02-01 10:43:11 +08:00
HydrogenSulfate
4fdcda7c60 fix bug in randaug, train_progressive and efficientnet_v2 2023-01-31 21:15:22 +08:00
HydrogenSulfate
7e12c73e0a polish progressive training code 2023-01-31 21:15:22 +08:00