3a1276d315
train_loss_func only used in train mode
2022-04-19 19:54:48 +08:00
7b020eb2aa
add paper citation
2022-04-19 19:45:19 +08:00
f834a22e71
update delimiter
2022-04-19 16:36:46 +08:00
24abea151a
support for multi optimizer case
2022-04-19 14:26:42 +08:00
3f84dcb44e
add random interpolation for UnifiedResize
2022-04-19 13:25:13 +08:00
c3018ebd39
add VAN-Classification code
2022-04-19 13:13:33 +08:00
a5a1c19273
Merge pull request #1851 from zhangxinyu-xyz/ISE_ReID
...
Release the inference code of ISE (ReID-CVPR2022)
2022-04-18 15:57:20 +08:00
83ed5195c3
fix: set use_fp16_test to True when AMP O2 is enabled
2022-04-18 06:14:43 +00:00
12d1b5f9a9
Release the inference code of ISE (ReID-CVPR2022)
2022-04-18 13:23:47 +08:00
1789da6422
fix bug
2022-04-18 11:26:32 +08:00
1db85b5d3b
remove pad
2022-04-18 11:07:47 +08:00
b242f52976
remove configs
2022-04-18 11:06:08 +08:00
52b5918dbc
Merge branch 'develop' of github.com:weisy11/PaddleClas into develop
2022-04-18 11:02:28 +08:00
a35cdd2aec
uncommit: sync bn is too slow to use and convert_sync_batchnorm() is not effective for BatchNorm
2022-04-14 08:19:39 +00:00
13d5e59051
fix: convert bn to sync_bn
...
the running_mean and running_var of bn would not be synchronized in dist,
so which leads to bug that eval loss in training is inconsistent with eval only.
2022-04-14 07:36:39 +00:00
efde56ffc6
fix: only fp16 evaluation is supported when ampO2 is enabled
2022-04-13 12:14:14 +00:00
bf12dffcd3
Merge pull request #1805 from RainFrost1/amp_o2
...
all model amp train config for tipc
2022-04-13 17:46:33 +08:00
474c918b27
fix: fix bug of batch_size statistics error
2022-04-13 09:19:30 +00:00
c46189bad0
fix: fix bug about calc loss in dist
2022-04-12 06:56:44 +00:00
af90cd7c59
update center loss config and related code
2022-04-12 13:07:53 +08:00
9de22673df
dbg
2022-04-08 14:29:03 +08:00
7f0b7a04cd
dbg
2022-04-08 10:59:18 +08:00
e651f3f62f
remove bnneck
2022-04-08 10:58:23 +08:00
d7a20aa967
dbg
2022-04-07 19:35:58 +08:00
9ab1ca3f0c
dbg
2022-04-07 18:31:45 +08:00
9c99e7cc6b
add bnneck, last stride=1
2022-04-07 16:59:09 +08:00
2ecdaddfc6
fix spell error for config.py
2022-04-07 06:57:32 +00:00
5615bc6cfd
change sampler
2022-04-06 20:14:29 +08:00
08582fe617
dbg
2022-04-06 19:54:15 +08:00
0993147af7
dbg
2022-04-06 19:49:10 +08:00
b761325faa
fix: fp32 eval by default when enable amp
...
If you want to eval by fp16 when enable amp, please set Amp.use_fp16_test=True, False by default.
2022-04-02 19:22:10 +08:00
96fbbad038
update mobilevit.py
2022-04-01 09:06:46 +00:00
44b9963b25
add mobilevit code
2022-04-01 08:51:42 +00:00
4b76c385e1
dbg
2022-04-01 11:42:49 +08:00
a5089348ee
dbg
2022-04-01 11:41:02 +08:00
fb2ddcfd64
update config
2022-04-01 11:39:43 +08:00
5f303937ae
dbg
2022-03-31 15:27:19 +08:00
fdfeeadff1
dbg
2022-03-31 15:15:50 +08:00
8408f8ef28
dbg
2022-03-31 15:12:05 +08:00
6618954c33
dbg and add configs
2022-03-31 15:10:50 +08:00
dbb8df64d5
add reid config
2022-03-31 15:06:06 +08:00
91b5337fdb
Merge pull request #1795 from cuicheng01/add_cswin
...
add cswin code and doc
2022-03-30 17:56:03 +08:00
86fed454c1
supoort -o new config param
2022-03-30 09:12:02 +00:00
a944603da0
fix log twice bug
2022-03-30 08:31:35 +00:00
f977c7c060
update cswin config
2022-03-30 03:40:27 +00:00
4839915056
update cswin_transformer.py
2022-03-29 12:01:04 +00:00
51e06d43f5
add cswin code and doc
2022-03-29 09:50:44 +00:00
84ae83da7a
Merge pull request #1762 from cuicheng01/develop
...
fix AccuracyScore metric
2022-03-28 16:32:20 +08:00
891fa1c093
fix AccuracyScore metric
2022-03-16 14:34:45 +00:00
b62b98d79f
feat: support mlu device and amp of mlu
2022-03-14 15:48:26 +08:00
456f9eac81
rename amp_O2 to amp_O2_ultra
2022-03-11 03:02:07 +00:00
218da4ddf9
feat: amp_O1 -> amp_O1_ultra, amp_O2 -> amp_O2_ultra
2022-03-10 11:10:37 +08:00
f68c098a4a
fix train acc log
2022-03-09 19:58:36 +08:00
8d52387a83
Merge pull request #1702 from Intsigstephon/develop
...
add deephash configure files and dch algorithm
2022-03-07 10:32:58 +08:00
158c7b4e35
fix: fix bug that overrided eval() can't be called in distributed
...
The eval() overrided can't be called because model is a DataParallel object in distributed.
2022-03-04 16:52:57 +08:00
7f0d54b121
fix some spelling error
2022-03-04 07:30:29 +00:00
32d1917085
Merge branch 'develop' of https://github.com/Intsigstephon/PaddleClas into develop
2022-03-04 07:08:30 +00:00
efdcf7c888
make code short;modify cifar10 data path
2022-03-04 07:07:35 +00:00
80ba57754f
Update DCH.yaml
2022-03-04 10:50:28 +08:00
4ea2f4493c
update cifar10 path
2022-03-03 06:30:47 +00:00
4fc82eef5a
feat: add the doc and demo about gallery2fc
...
add description doc and demo config
2022-03-01 10:34:29 +08:00
509f4d77e3
modify the cifar10 dataset format
2022-02-28 11:47:42 +00:00
1020f41899
use flatten instead of reshape for hrnet ( #1709 )
2022-02-28 19:12:53 +08:00
7595ba6d70
add AFD ( #1683 )
...
* add AFD
2022-02-28 19:11:50 +08:00
cef3cb25d9
update optimizer and some comment
2022-02-28 08:02:51 +00:00
7abf42b7a1
fix: rm some repvgg models not supported
...
remove RepVGG_B3, RepVGG_B2g2 and RepVGG_B3g2 that are not supported by PaddleClas.
2022-02-25 23:50:29 +08:00
4619d63273
fix: fix the download link, etc.
...
fix the pretrained and inference download link;
add use_ssld arg to TNT model.
2022-02-25 23:50:29 +08:00
fa45f73bdf
rm -rf binary_v2 configure file
2022-02-23 11:53:43 +00:00
2507be1a51
add deephash configs and dch algorithm
2022-02-23 11:50:39 +00:00
33e8e8348d
add static graph ResNet50 for benchmark
2022-02-21 08:37:02 +00:00
19f43aa21f
Merge pull request #1685 from littletomatodonkey/dev/improve_class_num_dist
...
improve distillation config
2022-02-17 15:58:41 +08:00
a25d37ea2b
Create GeneralRecognition_PPLCNet_x2_5_binary_v2.yaml
2022-02-14 19:45:41 +08:00
b31b07de45
improve distillation config
2022-02-14 16:34:01 +08:00
dc6281a6d4
add benchmark for tipc
2022-02-10 08:25:52 +00:00
6fec774fb6
Merge pull request #1599 from weisy11/fuse_lite_model
...
Fuse lite model
2022-01-26 19:39:49 +08:00
6f33833967
dbg
2022-01-25 17:40:48 +08:00
e95dcec819
dbg
2022-01-25 17:24:20 +08:00
88e6387b2c
add label_list file
2022-01-25 15:33:44 +08:00
42134cd8dd
fix: raise warning when using Global.class_num
2022-01-25 15:06:36 +08:00
0d22017e2e
fix: move class_num from Global to Arch
2022-01-25 15:06:36 +08:00
bb6581d21b
refactor: raise warning when gpu numbers is not 4
2022-01-25 15:06:36 +08:00
8f0bd5b582
fix: fix vdl makedir
2022-01-25 15:06:36 +08:00
10c93c55d1
fix: enable amp only in training
2022-01-25 11:58:07 +08:00
7040ce8314
refactor: change params to be consistent with amp
2022-01-25 11:58:07 +08:00
d6d5efe055
Merge pull request #1616 from JamesLim-sy/change_some_settings_for_clas_train_performance
...
Change some settings for clas model`s trainning performance
2022-01-25 11:29:27 +08:00
ce166b6ced
docs: fix invalid links
2022-01-17 21:14:38 +08:00
6963c25804
fix: fix bug
...
bug is that error rasied by calling update_res() when sublayer does not have _save_sub_res_hook() because nn.Sequential and nn.LayerList is not TheseusLayer.
2022-01-14 14:58:28 +08:00
a6a76f3d36
fix: args error
2022-01-14 14:58:28 +08:00
43fce425ac
fix: change the returned result from dict to list
2022-01-14 14:58:28 +08:00
3b9f629220
feat: support specify return_stages to update_res()
2022-01-14 14:58:28 +08:00
cd039a7b37
add save_dtype
2022-01-10 18:19:03 +08:00
d437bb0a7e
use fp32 to eval
2022-01-10 18:19:03 +08:00
bb19c1f7a6
fix eval bug
2022-01-10 18:19:03 +08:00
b2956c1b41
refine code
2022-01-10 18:19:03 +08:00
205592a3e3
fix amp with distribute bug
2022-01-10 18:19:03 +08:00
1a9b1782ef
fix: fix min_lr & warmup_lr
2022-01-07 11:52:30 +08:00
56c72a85a1
fix: fix lr
2022-01-07 11:52:30 +08:00
025feb6de9
fix: fix -1 in dims
2022-01-07 11:52:30 +08:00
7a0ed6f08d
rename
2022-01-07 11:52:30 +08:00
ee819393ac
fix: fix -1 in dims and ignore swapdim in static
2022-01-07 11:52:30 +08:00
HydrogenSulfate
flytocc
weishengyu
gaotingquan
zhangxinyu-xyz
Walter
cuicheng01
cuicheng01
huangqipeng
littletomatodonkey
Bin Lu
WangChen0902
Bin Lu
weishengyu
zhangbo9674