284e2a6756
refactor: mv all dataloaders to engine.dataloader_dict
2023-03-10 16:56:55 +08:00
efe0d45c99
refactor: rm irrelevant code
2023-03-10 16:56:55 +08:00
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
75a20ba557
refactor: add ClassModel to unify model forward interface
2023-03-10 16:56:55 +08:00
376d83d46e
refactor: simplify engine
2023-03-10 16:56:55 +08:00
c779cc14eb
adamwdl fix
2023-03-02 19:20:18 +08:00
bd9aee7d55
format MetaBIN_ResNet50_cross_domain.yaml and metabin.md
2023-02-28 15:01:21 +08:00
e0847f1800
Update pretrained backbone
2023-02-28 15:01:21 +08:00
f313a6d873
Support training without amp
2023-02-28 15:01:21 +08:00
4553d22cf1
Modify save_interval
2023-02-28 15:01:21 +08:00
74fa0cc203
Modify docstring
2023-02-28 15:01:21 +08:00
8229930391
Rename cfg
2023-02-28 15:01:21 +08:00
7c3bb2754b
Update files according to reviews
...
https://github.com/PaddlePaddle/PaddleClas/pull/2633
2023-02-28 15:01:21 +08:00
f4584bdb0d
Update cfg
2023-02-28 15:01:21 +08:00
a9b8432597
fix: wrong base class & simplify train func
2023-02-28 15:01:21 +08:00
f02a4630b2
Modify config
...
evaluate once every 400 iters
2023-02-28 15:01:21 +08:00
ac466b68da
Create MetaBNNeck
2023-02-28 15:01:21 +08:00
1be9c16a95
Update BNNeck
2023-02-28 15:01:21 +08:00
7a31d9a97f
fix: optimizer setting
2023-02-28 15:01:21 +08:00
21e76d08b6
Modify codes based on reviews
2023-02-28 15:01:21 +08:00
d79fb66e19
Create train func & cfg for MetaBIN
2023-02-28 15:01:21 +08:00
0cc6bc0bd3
Add regex support for selecting optim object
2023-02-28 15:01:21 +08:00
8d4a79e57f
Add cyclic learning rate
2023-02-28 15:01:21 +08:00
3c21282dfb
Create losses for MetaBIN
2023-02-28 15:01:21 +08:00
c3fa6eca86
Create backbone for MetaBIN
2023-02-28 15:01:21 +08:00
1070d9bec0
Create dataloader for MetaBIN
2023-02-28 15:01:21 +08:00
adb9930317
fix name
2023-02-28 14:28:23 +08:00
5604a13fac
fix name
2023-02-28 14:28:23 +08:00
f24e1f9bcf
cae config fix
2023-02-23 16:28:50 +08:00
fb763b7096
fix(dali): reset dataloader manually when using DALI dataloader during epoch training
2023-02-21 20:11:04 +08:00
1c68b63a66
fix some nots
2023-02-15 12:00:55 +08:00
23b011206a
fix randomapply
2023-02-15 11:17:18 +08:00
85f65ce76f
fix paddle2.4 hang problem
2023-02-14 10:50:27 +08:00
3f43784964
remove with_data_parallel in program.compile
2023-02-14 10:50:27 +08:00
811b483e30
fix: set dtype in paddle.to_tensor()
2023-02-10 15:51:53 +08:00
23f5af9f2a
add field vit to foundationvit's name
2023-02-07 17:38:50 +08:00
e8bf35d1b4
fix foundationvit load fail
2023-02-07 10:46:25 +08:00
83fc10cd0f
modify uniformer link
2023-02-06 19:28:30 +08:00
a170400d20
modify init
2023-02-01 10:43:11 +08:00
79cbd7350a
Aesthetic
2023-02-01 10:43:11 +08:00
4fdcda7c60
fix bug in randaug, train_progressive and efficientnet_v2
2023-01-31 21:15:22 +08:00
7e12c73e0a
polish progressive training code
2023-01-31 21:15:22 +08:00
8b8e0431ed
fix AttrDict import path
2023-01-31 21:15:22 +08:00
3a8b56801d
feat(model): add EfficientNetV2 code and fix AttrDict BUG
2023-01-31 21:15:22 +08:00
3c0dad0a48
modify
2023-01-31 19:57:43 +08:00
20a7c2944c
modifu config
2023-01-31 19:57:43 +08:00
1148712bb5
modify
2023-01-31 19:57:43 +08:00
5ea5b83a10
modify docs and config
2023-01-31 19:57:43 +08:00
b889101fd1
add docs and config
2023-01-31 19:57:43 +08:00
373a026a83
modify efficientnet_variant
2023-01-31 19:57:43 +08:00
54f7dd7484
watermark
2023-01-31 19:57:43 +08:00
add3ea238c
modify tipc
2023-01-20 14:08:06 +08:00
9ba23527b4
add swinv2
2023-01-20 14:08:06 +08:00
4786b2c96b
add swinv2
2023-01-20 14:08:06 +08:00
74de24f621
add swinv2
2023-01-20 14:08:06 +08:00
a5a3b0f567
Delete unnecessary files
2023-01-20 14:08:06 +08:00
272e75365b
modify swinv2
2023-01-20 14:08:06 +08:00
65e7a41a1d
add docs
2023-01-20 14:08:06 +08:00
7e616a16b5
modify init
2023-01-20 14:08:06 +08:00
f5e8df0e63
Some modifications
2023-01-20 14:08:06 +08:00
da95893bf2
supplement init
2023-01-20 14:08:06 +08:00
6994050983
add SwinTransformerV2
2023-01-20 14:08:06 +08:00
0a56120855
add swinV1 22k weights
2023-01-20 14:07:04 +08:00
3672d1f227
add swinV1 22k weights
2023-01-20 14:07:04 +08:00
5544dbaf8a
add ViT model for foundation models forward
2023-01-19 17:42:45 +08:00
216291618c
add the pretrained url
2023-01-06 20:29:07 +08:00
f6df698c4f
micro_block -> layer_type
2023-01-06 20:29:07 +08:00
81de331e00
rename to re_parameterize() for re-parameterization nets
2023-01-06 20:29:07 +08:00
d4d3d01384
support re_parameterize
2023-01-06 20:29:07 +08:00
f82871b1f8
add copyright & reference
2023-01-06 20:29:07 +08:00
e41f2a8fee
support PCALighting
2023-01-06 20:29:07 +08:00
963dcb9cac
support dbb module for ResNet
...
1. add DiverseBranchBlock module;
2. ResNet support dbb version using DiverseBranchBlock by setting micro_block="DiverseBranchBlock";
3. ResNet support official vb version by setting use_first_short_conv=False;
4. add ResNet18_dbb training config ResNet18_dbb.yaml.
2023-01-06 20:29:07 +08:00
4292c1a90d
fix turtle import bug
2023-01-06 10:57:05 +08:00
b05c8b1b7e
fix(retrieval): remove max_iter in retrieval.py to avoid empty data
2023-01-05 18:44:22 +08:00
2f331d8588
use scipy.sparse to speed up local query expansion
2023-01-05 15:13:04 +08:00
6871d601ff
speed up local QE by sparse matmul
2023-01-05 15:13:04 +08:00
c6865e255e
refactor(retrieval): polish retrieval.py
2023-01-05 15:13:04 +08:00
97f99cd826
refactor(retrieval): polish retrieval.py
2023-01-05 15:13:04 +08:00
8542967bef
修改FixMatchCCSSL成CCSSL
2023-01-04 13:42:00 +08:00
f8978a2f0c
修改cifar100参数配置
2023-01-04 13:42:00 +08:00
d8f049ae76
增加代码规范，删除无用空格
2023-01-04 13:42:00 +08:00
c5a29dbaec
代码规范
2023-01-04 13:42:00 +08:00
f073e97d22
增加cifar100参数yaml
2023-01-04 13:42:00 +08:00
009f347d64
修改空格等代码规范
2023-01-04 13:42:00 +08:00
f83ff59c97
增加代码规范，删除一些无用的function
2023-01-04 13:42:00 +08:00
692b8d8c1f
增加data的代码复用及RecModel的修改，代码已跑通
2023-01-04 13:42:00 +08:00
4db132444d
增加RecModel配合WideResNet代码以及参数转换成RecModel
2023-01-04 13:42:00 +08:00
7823f340b1
cifar10_4000跑出论文精度代码
2023-01-04 13:42:00 +08:00
9d054b2a7e
support NHWC data format
2022-12-28 16:06:10 +08:00
169682002d
Some modifications
2022-12-28 16:01:54 +08:00
7badd5bf6c
add metrics and postprocess
2022-12-28 16:01:54 +08:00
8d57bb31cf
modified DSNet config and TIPC txt
2022-12-22 14:55:46 +08:00
e069dedd7e
modified DSNet model names
2022-12-22 14:55:46 +08:00
28e094e097
add docs, config, model for DSNet
2022-12-22 14:55:46 +08:00
830852e745
modify configs
2022-12-22 14:54:25 +08:00
e238686e84
modify init
2022-12-22 14:54:25 +08:00
98d876a1b8
modify config
2022-12-22 14:54:25 +08:00
0140b38a80
add models
2022-12-22 14:54:25 +08:00
fdaf24ee78
add models
2022-12-22 14:54:25 +08:00
885e1bc05f
fix numpy int bug
2022-12-22 14:19:15 +08:00
7cdae10bcf
fix pksampler prob list shuffle bug
2022-12-22 12:01:05 +08:00
97398d9f12
fix export pretrained_model when it is None
2022-12-16 18:46:21 +08:00
20725dd770
fix xbm.py
2022-12-16 18:46:21 +08:00
51d71016ac
support web link for 'Global.pretrained_model' when export models
2022-12-16 18:46:21 +08:00
0288285c91
feat(loss): add TripletAngularMarginLoss_XBM and refine XBM queue
2022-12-16 18:46:21 +08:00
4060957669
fix(dali): add shuffle to prob_list in ExternalSource_RandomIdentity
2022-12-13 14:27:15 +08:00
b22752e2ea
refactor DALI
2022-12-13 14:27:15 +08:00
17a4b50ae2
rm singleton
2022-12-08 10:37:49 +08:00
9d69b63c6d
fix ct singleton
2022-12-07 14:14:22 +08:00
7cbc695227
use np for cpu tensor
2022-12-07 14:14:22 +08:00
19ed923799
fix typo
2022-12-07 14:14:22 +08:00
d70668cb6f
fix typo
2022-12-07 14:14:22 +08:00
a37cee70bf
remove global vars
2022-12-07 14:14:22 +08:00
fd4a97d144
lazy roll
2022-12-07 14:14:22 +08:00
a49e11db98
only for npu
2022-12-07 14:14:22 +08:00
20848e6abc
adapt roll op for swin transformer
2022-12-07 14:14:22 +08:00
4f01e3bc4f
add static training doc
2022-12-06 16:31:02 +08:00
b61da414e5
add uniformer lst
2022-12-02 19:45:59 +08:00
d7f73dd8ed
add relabel=True in ResNet50_ReID to avoid label excess
2022-12-02 15:00:46 +08:00
5b0a47bcdf
fix NextViT config
2022-11-30 16:25:30 +08:00
6cc6540ca5
add different seed for workers and replicas
2022-11-24 11:51:13 +08:00
b542416d67
add random shuffle in PKSampler
2022-11-24 11:51:13 +08:00
ec2029b821
Add NextViT code and docs
2022-11-23 14:59:55 +08:00
1ad4167fdc
fix engine.py
2022-11-22 16:47:47 +08:00
25ed25372a
fix engine.py
2022-11-22 16:47:47 +08:00
c07758b331
fix engine.py
2022-11-22 16:47:47 +08:00
fa52acd614
remove redundant import in pksampler
2022-11-22 16:47:47 +08:00
c26adddf33
remove redundant code in pksampler
2022-11-22 16:47:47 +08:00
7ff257ea69
fix random seed bug for pksampler in DDP
2022-11-22 16:47:47 +08:00
f04eb47fc3
replace strided_slice
2022-11-21 11:06:22 +08:00
aed02a213e
update pefd
2022-11-18 14:04:07 +08:00
7ee8471dfe
add pefd
2022-11-18 14:04:07 +08:00
faca0ba75d
add fixmatch config using 4gpus
2022-11-18 13:46:43 +08:00
cfab4c178a
feat: add pplcnetv2_small and pplcnetv2_big
2022-11-18 13:14:37 +08:00
1a8590a9bd
fix TprAtFpr metrics
2022-11-18 13:11:29 +08:00
c1a8ce4c94
fix error that sync bn should not be used on cpu
2022-11-16 16:05:53 +08:00
6d42c25cf2
fix_resnet_vd_nhwc_format
2022-11-16 10:40:40 +08:00
4924749e25
fix_celoss
2022-11-14 21:34:52 +08:00
996467bd14
update config and docs
2022-11-11 18:05:39 +08:00
c5884bb24f
add skd
2022-11-11 18:05:39 +08:00
cddc899f34
fix dataloader next
2022-11-09 19:01:00 +08:00
3d5ba52437
support image_orientation
2022-11-08 19:26:29 +08:00
7d9f4dcb59
change Tensor.numpy()[0] to float(Tensor) for 0-D tensor case
2022-11-01 14:37:11 +08:00
cb6d29aea0
update pulc_code_exists configs
2022-10-31 14:47:58 +08:00
426de2ddb3
update RepVGG configs
2022-10-31 14:31:27 +08:00
9873236bc8
fix: replace use_gpu, etc. by device
2022-10-31 10:43:00 +08:00
241572e49a
fix: debug
2022-10-31 10:43:00 +08:00
7e097f3c05
delete useless file and update 'print_dict' function
2022-10-27 19:15:32 +08:00
fd2f79943b
delete useless file and update 'print_dict' function
2022-10-27 19:15:32 +08:00
bcecbd1159
fix celoss bug
2022-10-27 14:17:09 +08:00
a623851224
fix: defer update_res() calling until after the object's __init__ has completed execution
2022-10-26 16:19:06 +08:00
316479d380
fix: add *args, **kwargs to init_net()
...
the argument may be "infer_add_softmax" used in exporting.
2022-10-26 16:19:06 +08:00
c032293a77
change judgment logic for multi device
2022-10-26 10:33:10 +08:00
0cec70bd22
[CustomDevice]add support for custom NPU, test=develop
2022-10-26 10:33:10 +08:00
3be87e0d91
fix ConsinFixmatch bug
2022-10-25 12:04:22 +08:00
944763d7a5
add fixmatch
2022-10-25 12:04:22 +08:00
184b684fd8
Merge pull request #2401 from HydrogenSulfate/fix_dali_static
...
Fix tensor conversion in static mode with dali loader
2022-10-21 12:08:26 +08:00
a14df4ac52
fix tensor conversion in static mode with dali loader
2022-10-20 12:03:03 +00:00
e3670a44a4
Merge pull request #2376 from cuicheng01/add_qrcode_code
...
[WIP]add qrcode code
2022-10-20 15:24:08 +08:00
3647da6d4a
Merge pull request #2383 from HydrogenSulfate/xbm_final
...
Add XBM model
2022-10-19 15:43:40 +08:00
09200a31f4
remove redundant code, fix bugs in lr.step, merge GoodsDataset into Vehicle
2022-10-19 07:18:21 +00:00
a5607e7d09
fix: update pretrained url
2022-10-18 17:48:31 +08:00
defcb638c3
fix: update pretrained url
2022-10-18 17:48:31 +08:00
ad3c657e39
fix: update VAN_tiny to VAN_B0
2022-10-18 17:48:31 +08:00
30cbb18321
update learning_rate.py
2022-10-17 15:51:48 +08:00
2cfd8dd828
add xbm
2022-10-17 15:45:45 +08:00
b83da15d27
support set shuffle by config
2022-10-17 11:24:57 +08:00
9dd59f4512
add qrcode code
2022-10-13 07:18:30 +00:00
61b4153907
add batch Tensor collate to simplify dali code in train/eval/retrival code
2022-10-13 12:05:50 +08:00
c87db7b9e3
update blur code
2022-10-11 13:46:27 +00:00
083205273d
add clarity_assessment code
2022-09-29 06:25:22 +00:00
b3ab418e80
refactor: mv the init_res of net to super().__init__()
...
Put the calling of update_res(), stop_after(), freeze_befor() to the construction method of the parent class. And the init_net() support to call stop_after() by config of Arch.
2022-09-28 20:13:19 +08:00
7513c0b52f
feat: support freeeze subnet
...
freeze subnet specified with the specified layer name by setting OutputTensor.stop_gradient=True
2022-09-28 20:13:19 +08:00
d670f2e497
rename config file ImageOrientation to PPLCNet_x1_0
2022-09-28 20:01:48 +08:00
bf91fbfbe4
add warning msg
2022-09-28 20:01:48 +08:00
75e1291528
debug
2022-09-28 20:01:48 +08:00
e31509ee81
fix hyperparams & mv to PULC
2022-09-28 20:01:48 +08:00
19840cb046
refactor: to be pythonic
2022-09-28 20:01:48 +08:00
e823f17853
feat: support training image orientation model
...
add the config of orientation model
add the preprocess op RandomRot90 that can rotate the img and return the orientation
add the CustomLabelDataset that support getting label by preprocess
refactor some preprocess ops to support dict parameter and return dict
2022-09-28 20:01:48 +08:00
db80bfb5ab
change return type from float to Constant when self.learning_rate is an float number
2022-09-27 19:46:20 +08:00
0160b8dd0d
fix
2022-09-27 11:56:42 +08:00
8f7e260218
Merge pull request #2326 from PaddlePaddle/fix_bug
...
fix bugs to adapt to the new framework
2022-09-20 19:05:42 +08:00
5957d242f2
Merge pull request #2323 from cuicheng01/add_table_attribute_doc
...
add table_attribute docs
2022-09-20 19:05:16 +08:00
50fc7d0eae
fix bugs to adapt to the new framework
2022-09-20 10:06:20 +00:00
6125fa941b
change Constant to ConstLR
2022-09-20 14:45:02 +08:00
74eb371dd6
add table_attribute docs
2022-09-20 04:37:52 +00:00
cc12db099c
fix Constant learning rate bug
2022-09-20 12:01:52 +08:00
c890a13c1f
Merge pull request #2313 from HydrogenSulfate/fix_LR
...
fix bug for warmup_steps setting
2022-09-19 15:05:25 +08:00
27101d3d88
fix bug for warmup_steps setting
2022-09-19 14:37:15 +08:00
cc46db1586
fix bugs to adapt to the new framework
2022-09-19 02:01:31 +00:00
0776f1c700
fix small bugs
2022-09-16 14:40:51 +08:00
57dcf7adb5
fix small bugs
2022-09-16 14:24:34 +08:00
7e072087a5
refactor learningrate.py
2022-09-16 13:59:11 +08:00
9344351493
Merge pull request #2219 from cuicheng01/fix_multilabel
...
fix multilabel
2022-09-15 10:54:28 +08:00
42758f5463
fix benchmark train's config for GeneralRecognitionV2, and polish TIPC docs
2022-09-14 08:54:22 +00:00
0b9f62262a
Merge branch 'develop' into fix_multilabel
2022-09-14 14:41:32 +08:00
9b12161b1d
add weighted soft labels loss function ( #2288 )
...
* add weighted soft labels loss function
add weighted soft labels loss function
* fix typo in docs/zh_CN/advanced_tutorials/knowledge_distillation.md
2022-09-14 14:23:26 +08:00
2ed68d5dba
Merge pull request #2264 from cuicheng01/add_table_attribute
...
add table_attribute_code
2022-09-14 14:17:11 +08:00
9a01999860
fix cae_large
2022-09-13 08:05:07 +00:00
8b0e643f54
update batchsize
2022-09-08 11:37:29 +00:00
gaotingquan
dolcexu
HydrogenSulfate
tianyi1997
zengshao0622
zh-hike
kangguangli
zhangyubo0722
zengshao0622
LittleMoon
kuizhiqing
cuicheng01
zhiqiu
user3984
weishengyu
user3984
dongshuilong
USTCKAY
cuicheng01
Lixin Luo