mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
5,063 Commits
23 Branches
12 Tags
292 MiB
Commit Graph

94 Commits (2200f30052634249ec6c985c711184e8fbff5a74)

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
Tingquan Gao 0675971d0b
rm fluid api (#2907) 2023-08-11 15:51:42 +08:00
Tingquan Gao 962c540ca4
debug: when using Piecewise.learning_rate while total epochs < 30 (#2901) 2023-08-07 15:26:49 +08:00
Tingquan Gao 907e5f7832
support Piecewise.learning_rate (#2898) 2023-08-04 12:14:19 +08:00
Tingquan Gao bb1596b8c3
compatibility with python 3.11 (#2878) 2023-07-20 10:50:52 +08:00
gaotingquan 042d1e7ef8 fix layer key name for dynamic lr in adamwdl optimizer 2023-05-26 15:40:48 +08:00
Yang Nie b66ee6384b fix RMSProp one_dim_param_no_weight_decay 2023-05-06 19:04:37 +08:00
Yang Nie c351dac67e add tinynet 2023-05-06 19:04:37 +08:00
gaotingquan 73f4d8e4ce to avoid cause issues for unset no_weight_decay models. 
there seems be a diff for optimizer about using [] and [{"params":}, {"params":}] params
 2023-04-12 20:55:38 +08:00
Yang Nie f36ffbc492 fix 2023-04-10 15:02:54 +08:00
Yang Nie beca8b2c1b add mobilenext 
add cooldown config

update optimizer

fix ParamAttr & update  test_tipc

fix tipc

update tipc config

remove docs of `_make_divisible`

refactor the implementation of "no weight decay"

fix model name

remove cooldown config
 2023-04-05 00:41:19 +08:00
Tingquan Gao 5d06a88a36 Revert "refactor: simplify engine" 
This reverts commit 376d83d46e.
 2023-03-14 16:47:13 +08:00
Tingquan Gao f2fc43baeb Revert "refactor: mv all dataloaders to engine.dataloader_dict" 
This reverts commit 284e2a6756.
 2023-03-14 16:47:13 +08:00
Tingquan Gao a1e840e0da Revert "refactor: iter_per_epoch -> max_iter" 
This reverts commit a38e42f644.
 2023-03-14 16:47:13 +08:00
Tingquan Gao 339be96ef5 Revert "refactor" 
This reverts commit 187f38ebdd.
 2023-03-14 16:47:13 +08:00
Tingquan Gao 7d41d24ce3 Revert "support Static" 
This reverts commit c30df63035.
 2023-03-14 16:47:13 +08:00
gaotingquan c30df63035 support Static 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 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 376d83d46e refactor: simplify engine 2023-03-10 16:56:55 +08:00
dolcexu c779cc14eb adamwdl fix 2023-03-02 19:20:18 +08:00
tianyi1997 74fa0cc203 Modify docstring 2023-02-28 15:01:21 +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 0cc6bc0bd3 Add regex support for selecting optim object 2023-02-28 15:01:21 +08:00
tianyi1997 8d4a79e57f Add cyclic learning rate 2023-02-28 15:01:21 +08:00
zh-hike f83ff59c97 增加代码规范，删除一些无用的function 2023-01-04 13:42:00 +08:00
zh-hike 7823f340b1 cifar10_4000跑出论文精度代码 2023-01-04 13:42:00 +08:00
HydrogenSulfate 7d9f4dcb59 change Tensor.numpy()[0] to float(Tensor) for 0-D tensor case 2022-11-01 14:37:11 +08:00
dongshuilong 3be87e0d91 fix ConsinFixmatch bug 2022-10-25 12:04:22 +08:00
dongshuilong 944763d7a5 add fixmatch 2022-10-25 12:04:22 +08:00
HydrogenSulfate 30cbb18321 update learning_rate.py 2022-10-17 15:51:48 +08:00
HydrogenSulfate 2cfd8dd828 add xbm 2022-10-17 15:45:45 +08:00
HydrogenSulfate db80bfb5ab change return type from float to Constant when self.learning_rate is an float number 2022-09-27 19:46:20 +08:00
HydrogenSulfate 6125fa941b change Constant to ConstLR 2022-09-20 14:45:02 +08:00
HydrogenSulfate cc12db099c fix Constant learning rate bug 2022-09-20 12:01:52 +08:00
HydrogenSulfate 27101d3d88 fix bug for warmup_steps setting 2022-09-19 14:37:15 +08:00
HydrogenSulfate 0776f1c700 fix small bugs 2022-09-16 14:40:51 +08:00
HydrogenSulfate 57dcf7adb5 fix small bugs 2022-09-16 14:24:34 +08:00
HydrogenSulfate 7e072087a5 refactor learningrate.py 2022-09-16 13:59:11 +08:00
zengshao0622 7b50ce6585 merge CAE 2022-09-08 08:11:25 +00:00
HydrogenSulfate 43410aa852 update config, add amp eval for retrieval 2022-06-21 23:03:56 +08:00
HydrogenSulfate 790815f430 refine code and docs 2022-05-05 22:14:07 +08:00
HydrogenSulfate 16f910b451 add m1 and baseline config 2022-05-05 19:55:08 +08:00
HydrogenSulfate 0b1481402b merge devevelop 2022-05-05 14:42:06 +08:00
littletomatodonkey bb13f3c4f5
fix single card dist (#1889) 
* fix single card logit

* fix distillation yaml files
 2022-05-05 09:48:56 +08:00
HydrogenSulfate 6149e719b3 refine code 2022-04-25 14:14:20 +08:00
HydrogenSulfate 674447f63e refine code 2022-04-25 11:25:44 +08:00
HydrogenSulfate bc6e7f5cf5 update code 2022-04-22 15:26:05 +08:00