mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
5,061 Commits
23 Branches
12 Tags
292 MiB
Commit Graph

1730 Commits (3dac3be5067abe0155d56533cbee17e9cd2ff6a5)

Author SHA1 Message Date
zhuyipin 3dac3be506
adapt AdaptiveAvgPool2D for npu for PPHGNet (#3163) (#3223) 2024-08-26 11:57:09 +08:00
Tingquan Gao 82034d1b3f fix: there may not be weight ratio in multilabel dataset label (#3226) 2024-08-23 14:40:09 +08:00
zhuyipin 28dc67e3e2
convert npu roll op into paddle roll (#3139) 2024-05-15 17:11:28 +08:00
cuicheng01 168097fd61
remove PP-HGNetV2_B7 config (#3024) 2023-10-30 20:21:52 +08:00
zhangyubo0722 25b65bb796
del load pretrained from url for resnet (#2998) 
* del load pretrained from url for resnet

* del load_dygraph_pretrain_from_url

* modify save_load

* modify save_load
 2023-10-30 13:45:53 +08:00
cuicheng01 aa5d103139
[cherry-pick] update PP-HGNetV2 (#2994) 
* add hgnetv2 (#2987)

* support load ssld state1 pretrain (#2988)

* update PP-HGNetV2
 2023-10-07 16:44:38 +08:00
cuicheng01 bfea8e83a6
Release/2.5.1 (#2990) 
* add hgnetv2 (#2987)

* support load ssld state1 pretrain (#2988)
 2023-09-27 00:03:01 +08:00
cuicheng01 43e6382aa3
add hgnetv2 (#2987) (#2989) 2023-09-26 23:59:38 +08:00
gaotingquan 10cf2775e4 fix Infer.transforms.ResizeImage 2023-09-19 16:02:03 +08:00
gaotingquan b462847663 fix 2023-09-19 16:02:03 +08:00
zhangyubo0722 9e9d8c9d2b support http pretrained 2023-09-12 18:00:49 +08:00
zhangyubo0722 a119eb4191
fix hgnet kwargs (#2950) 2023-09-01 23:45:04 +08:00
zhangyubo0722 82317a21e3
del head_init_scale (#2948) 2023-09-01 20:15:35 +08:00
zhangyubo0722 f4de50226a
fix gbk (#2943) 
* fix gbk

* fix_bug
 2023-09-01 19:29:25 +08:00
gaotingquan 8312dc3677 debug: fix model name 2023-08-29 16:40:37 +08:00
Tingquan Gao 48fb2c86f2
to be compatible with training and evaluation (#2932) 2023-08-29 11:43:41 +08:00
zhangyubo0722 a60d18a3d8
[uapi]save_predict_result (#2928) 
* save_predict_result

* save_predict_result
 2023-08-28 19:40:51 +08:00
Tingquan Gao b34ed83708
always log 'topk=1' when k < output_dims to ensure consistent log formatting (#2925) 2023-08-28 14:55:32 +08:00
Tingquan Gao 28ef1c00d8
[cherry-pick] some fix (#2920) 
* fix model name

* fix: bug when distillation

* modify some default hyperparams to adapt to fine-tune downstream tasks

1. unset EMA because of the relatively small size of most downstream dataset;
2. use mean and std of IMN.
 2023-08-25 22:02:57 +08:00
gaotingquan 353c3f512b debug: when using Piecewise.learning_rate while total epochs < 30 2023-08-07 11:30:25 +08:00
Tingquan Gao 4247fac82e
support Piecewise.learning_rate (#2899) 2023-08-04 12:16:01 +08:00
wuyefeilin 657037c4e7
add dataset alias for PaddleX (#2892) 2023-08-02 10:41:40 +08:00
cuicheng01 4da6f35bf2 support infer nested directory images 2023-06-29 19:43:40 +08:00
baocheny 75a5bb17ba add 2 more custom devices intel_gpu and apple mps 2023-06-29 19:42:38 +08:00
baocheny 3d0c0eb59d add 2 more custom devices intel_gpu and apple mps 2023-06-29 19:42:38 +08:00
Bobholamovic bda65e0c87 Remove ClasModels_general_quantization.yaml 2023-06-26 14:20:38 +08:00
Bobholamovic de5c4e1b1c Change vdl dir 2023-06-26 14:20:38 +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
gaotingquan 07b597f56e increase bs to avoid oom 2023-06-06 11:19:01 +08:00
gaotingquan caa6393cd4 set drop_last to False in train data 2023-06-06 11:19:01 +08:00
gaotingquan cf5d629a64 fix 2023-06-06 11:19:01 +08:00
gaotingquan 4643fdee09 update pretrained url 2023-06-06 11:19:01 +08:00
mmglove dd9b186e82 ppcls/utils/profiler.py 2023-06-05 21:23:35 +08:00
mmglove 54d27a1204 fix profiler 2023-06-05 21:23:35 +08:00
mmglove 259c0ca9de fix profiler 2023-06-05 21:23:35 +08:00
gaotingquan bdfa1feb2f update for amp config refactoring 2023-05-29 19:52:09 +08:00
gaotingquan 09817fe859 complete amp args 2023-05-29 19:52:09 +08:00
gaotingquan b3f7e3b974 unify comments 2023-05-29 19:52:09 +08:00
gaotingquan 8405882f11 debug 2023-05-29 19:52:09 +08:00
gaotingquan 0f86c55576 add amp args, use_amp=False 2023-05-29 19:52:09 +08:00
gaotingquan 2d8346cd3b fix _init_amp when export 2023-05-29 19:52:09 +08:00
gaotingquan f67cfe2c2a fix ema: set_value() -> paddle.assign() 2023-05-26 15:40:48 +08:00
gaotingquan 2823e48be5 fix head_init_scale 2023-05-26 15:40:48 +08:00
gaotingquan 042d1e7ef8 fix layer key name for dynamic lr in adamwdl optimizer 2023-05-26 15:40:48 +08:00
gaotingquan 80ae9079cd add clip finetune config 2023-05-26 15:40:48 +08:00
gaotingquan 6d924f85ee fix for clip 
1. fix bias_attr to False for conv of PatchEmbed;
2. support return_tokens_mean for Head of CLIP;
3. support remove_cls_token_in_forward for CLIP;
4. support head_init_scale argument for ViT backbone;
5. support get_num_layers() and no_weight_decay() for ViT backbone.
 2023-05-26 15:40:48 +08:00
gaotingquan 74e6c8aa33 add fp32 and ampo2 ultra configs 2023-05-25 16:57:16 +08:00
gaotingquan f469dfe8d2 decrease bs 2023-05-25 16:57:16 +08:00
gaotingquan 53ac4675ad warmup 5 epochs 2023-05-25 16:57:16 +08:00