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
e4380ce517
fix height error
2022-02-15 21:31:36 +08:00
b6cf278663
change MultiScaleSamplerDDP into MultiScaleSampler
2022-02-15 21:31:23 +08:00
fe9f519b22
modify according to review
2022-02-15 21:30:08 +08:00
9ac9cb8aa5
add config file
2022-02-15 21:25:53 +08:00
f2dde17623
multi scale sampler and dataset
2022-02-15 21:25:25 +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
00fb3f7519
feat: support PVTV2
2022-01-07 11:52:30 +08:00
a53b636829
feat: support PVTV2
2022-01-07 11:52:30 +08:00
e0a6e5bf38
fox dist err ( #1621 )
...
* fox dist err
* fix init
* fix init
2022-01-06 09:46:52 +08:00
f015860645
drop useless settings
2022-01-05 13:15:19 +00:00
aea712cc87
add dist of rec model ( #1574 )
...
* add distillation loss func and rec distillation
2022-01-05 19:25:36 +08:00
24a51ae064
first
2022-01-04 07:20:31 +00:00
304bafb735
Merge pull request #1610 from TingquanGao/dev/fix_theseus
...
fix: upgrade replace_sub() to upgrade_sublayer()
2021-12-31 12:15:18 +08:00
d6aeba6f56
fix: upgrade replace_sub() to upgrade_sublayer()
...
supplement to PR #1581
2021-12-30 10:59:20 +00:00
6e13ff3068
fix: use hasattr() to check if collate_fn is in dataloader
...
fix bug caused by PR #1596
2021-12-30 16:35:05 +08:00
cabc7a0f83
fix: replace reg exp with layer name
2021-12-28 15:24:50 +08:00
71cb728b07
fix: rename to upgrade_sublayer()
2021-12-28 15:24:50 +08:00
1e696ac22b
fix: remove unnecessary register_hook() call & pre-commit
2021-12-28 15:24:50 +08:00
a86c4b290e
add license
2021-12-28 15:24:50 +08:00
721ac0bf61
refactor: simplify code
...
1. remove WrapLayer and wrap_theseus;
2. support call update_res() one more;
3. optim parse_pattern_str() to return list of layer parsed.
2021-12-28 15:24:50 +08:00
56911b573b
refactor: rename replace_sub() func to ?
2021-12-28 15:24:50 +08:00
0f126b75da
refactor: strengthen parse_pattern_str() func
2021-12-28 15:24:50 +08:00
8d0b0d4b0a
refactor: extract _parse_pattern_str() func
2021-12-28 15:24:50 +08:00
18dec0744a
fix: fix problems commented in reviewing
2021-12-28 15:24:50 +08:00
41296972a4
fix: fix comments
2021-12-28 15:24:50 +08:00
f8ee6c0f86
fix: fix result returned by stop_after
2021-12-28 15:24:50 +08:00
cf205e1379
fix: fix result returned by _find_layers_handle
2021-12-28 15:24:50 +08:00
b0ae3a1210
fix: unify the pattern of layer's name
2021-12-28 15:24:50 +08:00
7da2a997e9
fix: save latest model every epoch
2021-12-27 22:04:26 +08:00
377a7b4b2f
dbg
2021-12-27 20:35:42 +08:00
9a1d35ba3b
add license info
2021-12-27 20:16:56 +08:00
87f508e9f9
dbg
2021-12-27 19:37:00 +08:00
5d53e9f152
fix: raise warning when setting batch_transform_ops and TopkAcc
2021-12-24 21:22:52 +08:00
b662ed34ac
dbg
2021-12-24 11:15:27 +08:00
18d99b012b
move gallery layer into extractor
2021-12-24 11:06:42 +08:00
25edd1c0d8
refactor code
2021-12-23 20:51:15 +08:00
d5637367a9
add export method
2021-12-23 20:35:10 +08:00
932e0eace1
dbg
2021-12-23 20:29:05 +08:00
0f35f706b6
Fix static training speed ( #1590 )
...
* fix training speed
* update config setting method
2021-12-23 11:13:51 +08:00
f45f9ee4d4
Merge pull request #1585 from zhangbo9674/dev/resnet50_optimize
...
Accelerate dynamic graph amp training
2021-12-21 17:31:25 +08:00
558f03d684
refine code
2021-12-21 06:30:13 +00:00
28061f537c
refine optimizer init logice
2021-12-21 06:28:13 +00:00
7aa9f1c6ea
Merge pull request #1588 from cuicheng01/add_new_config
...
add some new configs
2021-12-21 14:03:51 +08:00
2e578335cd
add some new configs
2021-12-20 08:10:39 +00:00
b54ee04491
Accelerate dynamic graph amp training
2021-12-20 06:36:56 +00:00
7732a69f1b
fix: fix key error in distillation
2021-12-16 18:21:08 +08:00
b6a7c53182
add feature extract
2021-12-15 10:39:26 +08:00
897760f073
Merge pull request #1544 from cuicheng01/update_vit
...
update vit
2021-12-14 14:40:14 +08:00
b3922c96f5
Merge pull request #1436 from TingquanGao/dev/update_whl
...
update whl
2021-12-14 12:15:46 +08:00
f5450c3d66
delete vit_huge config
2021-12-14 03:10:07 +00:00
c941144568
update gallery2fc
2021-12-14 10:34:40 +08:00
83d1b411c5
update vit
2021-12-10 09:56:33 +00:00
8d22f0250e
Merge pull request #3 from PaddlePaddle/develop
...
Develop
2021-12-10 17:26:22 +08:00
524190a775
Merge pull request #1543 from RainFrost1/tipc_batch_size
...
fix tipc batch_size bug
2021-12-10 16:57:36 +08:00
ab187e21cc
fix tipc inference batch_size bug
2021-12-10 08:05:36 +00:00
51c3a34275
Merge pull request #1540 from weisy11/refor_quant
...
Refor quant
2021-12-10 14:59:39 +08:00
534037d145
dbg
2021-12-10 11:14:14 +08:00
6510da8fca
dbg
2021-12-09 20:15:25 +08:00
ad1a2fd137
move slim into arch
2021-12-09 20:08:57 +08:00
7c6567cc6b
dbg
2021-12-09 18:08:16 +08:00
6c5d1ebc28
add pruner and quanter for theseus
2021-12-09 14:51:40 +08:00
f9ee1befbf
Merge pull request #1533 from Intsigstephon/modify_binary_configure
...
modify binary model configure
2021-12-09 14:47:18 +08:00
63f7fdbf9c
add logger
2021-12-08 20:02:13 +08:00
823074d894
dbg
2021-12-08 19:56:30 +08:00
d05d9d8d65
update functions
2021-12-08 19:48:59 +08:00
be220a5f09
move file to ppcls
2021-12-08 19:47:43 +08:00
94cce6422f
fix augmix bug
2021-12-08 07:53:33 +00:00
ecbc2b998f
modify binary model configure
2021-12-07 07:24:01 +00:00
a3b54f15d5
fix export quant_model
2021-12-03 07:39:31 +00:00
71abe2e9bf
update PP-LCNet config
2021-12-01 04:08:38 +00:00
5dad991c2a
update se_resnext_vd.py
2021-11-30 15:06:05 +00:00
bc16eed9f9
Merge pull request #1453 from cuicheng01/develop
...
fix class_num in quickstart
2021-11-22 12:00:56 +08:00
ee3c643cc1
update combined loss for accelerate classification training speed
2021-11-19 08:35:47 +00:00
dd08d344af
fix class_num in quickstart
2021-11-17 15:04:04 +00:00
9a23b4326a
Merge pull request #1444 from RainFrost1/reid
...
添加车辆ReID的PPLCNet 2.5x模型
2021-11-17 15:03:29 +08:00
d53a06c625
fix: fix download link
2021-11-17 15:02:20 +08:00
c02ec9a3b3
update vehcile reid model PPLCNet2.5x
2021-11-16 06:24:57 +00:00
c39838778b
add vehcile reid model PPLCNet2.5x
2021-11-16 06:22:03 +00:00
f7ccc874e2
fix dali distributed eval bug
2021-11-16 11:09:21 +08:00
423144c097
fix some configs
2021-11-15 07:26:58 +00:00
ae6cb7d529
feat: support MixNet
2021-11-15 06:53:34 +00:00
6e4bf593fb
Merge pull request #1390 from Intsigstephon/feature_binary_model
...
add Binary general recog configure
2021-11-12 15:25:00 +08:00
fb631b38fb
update esnet.py
2021-11-11 12:51:58 +00:00
d868a63764
Add ESNet code and pretrained models
2021-11-11 06:00:32 +00:00
af25eaf799
docs: update flower102 label map list
2021-11-10 00:16:23 +08:00
720c451bc4
fix: fix batch size to 64 * 4
2021-11-10 00:16:23 +08:00
7ebb0b8ab1
docs: add reference link
2021-11-08 06:36:02 +00:00
3b4a45f8ab
Update deephashloss.py
2021-11-06 23:32:19 +08:00
f7ee2b98a6
Update deephashloss.py
2021-11-06 23:14:40 +08:00
13df9b9df8
Update GeneralRecognition_PPLCNet_x2_5_binary.yaml
2021-11-06 23:12:56 +08:00
61a09b0d44
Update GeneralRecognition_PPLCNet_x2_5_binary.yaml
2021-11-06 23:12:29 +08:00
67d982c30e
fix csp refer ( #1404 )
2021-11-05 13:54:10 +08:00
d8fbc1b36b
Merge pull request #1407 from cuicheng01/develop
...
update vision_transformer.py
2021-11-05 11:09:44 +08:00
7875e83d9e
update vision_transformer.py
2021-11-05 02:53:10 +00:00
5aba5f898e
Merge pull request #1396 from TingquanGao/dev/sup_docs
...
docs: supplement docs
2021-11-04 21:02:17 +08:00
53da62b05e
Merge pull request #1395 from littletomatodonkey/dev/add_refer
...
add reference
2021-11-04 19:17:00 +08:00
08952deb88
update codes
2021-11-04 10:47:13 +00:00
8ac51f7416
fix: adapt to release 2.3
2021-11-04 09:48:34 +00:00
9f2f62f3ae
Update pp_lcnet_variant.py
2021-11-04 16:58:17 +08:00
17fc4595b3
Create pp_lcnet_variant.py
2021-11-04 16:44:56 +08:00
cad5ce842a
Update __init__.py
2021-11-04 16:44:16 +08:00
6f13c5b798
rename PPLCNet_x2_5_Tanh
2021-11-04 08:37:21 +00:00
886856196e
fix ema reference
2021-11-04 16:29:12 +08:00
cae027605c
add reference
2021-11-04 16:18:26 +08:00
df03b4a022
add Binary general reocg configure
2021-11-03 10:09:34 +00:00
7a17f72fc2
fix seed=0 bug
2021-11-01 06:16:24 +00:00
a5d0e37b02
Merge pull request #1341 from RainFrost1/googlenet_bug
...
fig goooglenet distributed eval bug
2021-10-29 10:28:37 +08:00
d3a1a1fc45
fix: fix type of label to int64
2021-10-28 17:22:39 +08:00
ed459a2a16
refactor: adapt to static graph in deprecating MixCELoss
2021-10-27 19:47:43 +08:00
5025d09fd8
fix: fix a DeprecationWarning & style
2021-10-27 19:47:43 +08:00
ba2dd01a13
refactor: deprecate MixCELoss
2021-10-27 19:47:43 +08:00
278f6d8050
fig goooglenet distributed eval bug
2021-10-26 11:56:30 +00:00
a0eb34a642
Add npu supporting ( #1324 )
2021-10-22 11:02:29 +08:00
cc00a51af7
Merge pull request #1322 from RainFrost1/train_without_eval
...
fix train without eval bug
2021-10-21 15:35:05 +08:00
53ed9239a0
Merge pull request #1320 from RainFrost1/develop
...
fix clas distributed eval bug
2021-10-21 15:31:01 +08:00
fd6f1ad2ca
fix clas distributed eval bug
2021-10-21 03:47:03 +00:00
06382519cf
fix train without eval bug
2021-10-21 02:39:27 +00:00
c93d638f4c
fix clas distributed eval bug
2021-10-20 11:22:37 +00:00
6f2a096be3
fix ips info ( #1306 )
2021-10-19 16:20:35 +08:00
e4bb18766a
Merge pull request #1245 from RainFrost1/benchmark
...
add version 1 for benchmark
2021-10-19 10:18:16 +08:00
0e20e60f6b
fix slim load pretrained model bug
2021-10-18 10:07:14 +00:00
3c148cb56a
update return res method and fix amp bug ( #1309 )
...
* fix amp bug; update return res method
* support index for list object for return res
2021-10-15 18:25:50 +08:00
ab92b397e0
Merge pull request #1300 from TingquanGao/dev/fix_config
...
fix: fix config
2021-10-15 15:37:19 +08:00
70baba549a
Merge pull request #1293 from cuicheng01/develop
...
Add PP-LCNet docs
2021-10-15 14:24:44 +08:00
612eedbbc5
Update recognition config
2021-10-14 11:57:00 +00:00
2677d41998
update recognition configs
2021-10-14 11:13:57 +00:00
c2a9f8830e
update profiler
2021-10-13 09:30:11 +00:00
272bc9481d
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleClas into benchmark
2021-10-13 09:26:28 +00:00
8a5624f835
fix: fix config
2021-10-12 09:05:03 +00:00
f8b420946c
fix cspnet ( #1282 )
...
* fix cspnet
* minor fix
2021-10-11 17:23:31 +08:00
3b5f2688aa
fix distributied training bug for rec slim model
2021-10-09 08:42:12 +00:00
7dcb2d4fd0
fix: raise exception
...
raise exception about using no_weight_decay of AdamW in static graph
2021-09-30 10:48:36 +00:00
c7aeec28e2
fix: support static graph
2021-09-30 06:57:17 +00:00
0dccfb917d
fix: interpolation maybe be 0
2021-09-30 06:49:41 +00:00
879e461475
Merge pull request #1273 from weisy11/develop
...
remove trick code
2021-09-29 11:34:06 +08:00
c4d54dd0e0
remove trick code
2021-09-29 10:59:16 +08:00
890f43f038
Merge pull request #1267 from RainFrost1/arcmargin
...
update pretrained_model for vehicle,loge model
2021-09-27 20:09:02 +08:00
41041092b5
add comment for pk sampler
2021-09-27 15:52:19 +08:00
ee1bc18f3a
dbg
2021-09-27 15:31:31 +08:00
5aa57d2ce0
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleClas into arcmargin
2021-09-27 07:16:28 +00:00
f0bf51b341
update pretrained_model for vehicle,loge model
2021-09-27 06:31:45 +00:00
fe6f614680
Update multilabel
2021-09-27 03:00:37 +00:00
a90881c99f
Merge branch 'develop' into add_multilabel
2021-09-26 22:47:20 +08:00
da25931466
update lr
2021-09-26 17:09:30 +08:00
a98bd7a73c
update vehicle and logo config
2021-09-26 16:42:08 +08:00
8595d18945
update format
2021-09-26 16:07:05 +08:00
be80612175
update Inshop config
2021-09-26 15:51:18 +08:00
2483b79c5d
Merge branch 'PaddlePaddle:develop' into develop
2021-09-26 15:48:45 +08:00
5992be4adf
add multilabel feature
2021-09-26 07:20:11 +00:00
af9aae730e
add multilabel feature
2021-09-26 07:05:13 +00:00
b84e4352b1
dbg
2021-09-26 14:28:12 +08:00
de859b4a3d
fix: compatible with opencv under version 4.4.0
2021-09-26 13:22:38 +08:00
ab5be02f57
Merge pull request #1257 from cuicheng01/fix_googlenet
...
fix googlenet avg-pool
2021-09-24 11:56:31 +08:00
6529765a0b
update pksampler
2021-09-23 19:35:35 +08:00
b7bab1e648
fix googlenet avg-pool
2021-09-23 08:29:07 +00:00
756b6fb3de
Update GeneralRecognition_PPLCNet_x2_5.yaml
2021-09-23 06:36:12 +00:00
af25e25640
modify format
2021-09-23 11:22:25 +08:00
16985020a5
Update GeneralRecognition_PPLCNet_x2_5.yaml
2021-09-23 03:20:34 +00:00
126246832b
Update GeneralRecognition_PPLCNet_x2_5.yaml
2021-09-23 02:51:50 +00:00
929b845b2f
Update GeneralRecognition_PPLCNet_x2_5.yaml
2021-09-23 02:50:08 +00:00
9245804e41
Update GeneralRecognition_LCNet_x2_5.yaml
2021-09-23 02:23:44 +00:00
a37332d326
Add GeneralRecognition config
2021-09-22 12:19:16 +00:00
9f2ab06ec2
add profiler
2021-09-22 08:29:44 +00:00
f91bc7ba0b
perf: add parameter validation ( #1249 )
...
When using warm up, the total epoch num must be greater than warm up epoch num. Otherwise,
there will be raising warning and warm up epoch num will be set to total epoch num.
2021-09-22 14:35:37 +08:00
9e97569953
update sample method
2021-09-22 14:29:33 +08:00
283f9fa9b6
fix: fix swin training config
2021-09-18 12:44:51 +08:00
f6cfa0471c
dbg
2021-09-18 11:13:54 +08:00
7830860bbf
rm writer dataset and sampler
2021-09-18 11:11:48 +08:00
6497727bbc
Merge branch 'PaddlePaddle:develop' into develop
2021-09-18 11:04:59 +08:00
862c2147a5
Merge pull request #1169 from TingquanGao/dev/fix_augmentation
...
fix: fix augmentation
2021-09-17 20:51:11 +08:00
f5b32a02ea
fix: fix the training configs of deit, swin, twins
2021-09-17 20:17:38 +08:00
1f8cfbd69d
fix: fix augmentation
...
Fix RandomErasing, RandAugment to be consistent with Timm and compatible with earlier PaddleClas.
Add ColorJitter implemented by PaddleVision and TimmAutoAugment borrowed from Timm Lib.
2021-09-17 11:00:00 +00:00
ef2fd19bb0
Merge pull request #1243 from RainFrost1/arcmargin
...
fix pact bug for circlemargin arcmargin cosmargin
2021-09-17 18:56:03 +08:00
9bc2041e74
Merge pull request #1228 from TingquanGao/dev/support_pil_resize
...
feat: support pil resize
2021-09-17 18:54:07 +08:00
ba9b708acb
Merge pull request #1174 from TingquanGao/dev/add_adamw
...
feat: add AdamW
2021-09-17 18:53:18 +08:00
36aeefcf4c
Merge pull request #1064 from TingquanGao/dev/Support_enable_cutmix_mixup
...
support to enable mixup and cutmix at same time
2021-09-17 18:51:34 +08:00
94433634c0
fix: fix Linear & support warmup start lr & support Cosine eta_min
...
Support setting warmup start lr and eta_min in Cosine.
Fix bug that Linear can not decay to end_lr when setting warmup.
2021-09-17 18:41:55 +08:00
0bdb16af8b
add pk_sampler
2021-09-17 18:08:35 +08:00
bd68a9cb8b
update Vehicle yamls
2021-09-17 07:42:08 +00:00
a9a13d5984
update Vehicle yamls
2021-09-17 07:38:21 +00:00
48494ec051
Merge pull request #1213 from cuicheng01/develop
...
Add PP-LCNet codes and configs
2021-09-17 15:29:50 +08:00
d7181f6451
Merge pull request #1241 from cuicheng01/fix_Alexnet_lr_bug
...
fix Alexnet lr bug
2021-09-17 15:26:47 +08:00
18e1cf040b
fix pact bug for circlemargin arcmargin cosmargin
2021-09-16 12:17:02 +00:00
43aeb572a3
fix Alexnet lr bug
2021-09-16 08:08:41 +00:00
4d1f61c407
fix Alexnet lr bug
2021-09-16 07:54:16 +00:00
1abbc82635
Merge pull request #1235 from RainFrost1/slim
...
Update MobileNetV3_large_x1_0_quantization.yaml
2021-09-15 16:01:25 +08:00
36dc2ef164
Update MobileNetV3_large_x1_0_quantization.yaml
2021-09-15 15:32:31 +08:00
85e2407e46
fix mix training for static program ( #1234 )
2021-09-15 14:36:11 +08:00
64c370008b
feat: support pil resize
...
Support PIL resizse with PIL interpolation to train transformer.
Almost all vision transformer models need using PIL.Image.BICUBIC
as interpolation in resize.
2021-09-15 06:29:22 +00:00
d98b881603
Merge pull request #1208 from weisy11/fix_bug_of_theseus
...
dbg theseus
2021-09-15 14:04:51 +08:00
600067f4fc
dbg
2021-09-15 11:35:49 +08:00
e916259508
update return_res method
2021-09-15 11:03:46 +08:00
94c9900ece
add seed
2021-09-14 04:06:37 +00:00
74622af482
Merge pull request #1093 from RainFrost1/slim
...
添加slim功能
2021-09-13 19:11:43 +08:00
4dc145700a
Merge pull request #1223 from cuicheng01/add_efficientnet_config
...
Add EfficientNet config
2021-09-13 17:42:05 +08:00
8e47811d99
Update PPLCNet
2021-09-13 09:29:57 +00:00
9eb098a110
Update PPLCNet config
2021-09-13 09:00:39 +00:00
7df35e4875
Add EfficientNet config
2021-09-13 08:12:06 +00:00
d470f34c64
Update code and docs
2021-09-13 03:18:37 +00:00
8e85ef4775
update slim
2021-09-10 03:09:03 +00:00
b578662b32
perf: add OpSampler to support multiple ops
2021-09-08 12:53:48 +00:00
4150df912e
Add LCNet codes and config
2021-09-07 16:14:40 +00:00
3f0b406fb2
fix tnt inference bug when bs > 1
2021-09-07 03:46:29 +00:00
5131956d15
dbg theseus
2021-09-06 16:18:57 +08:00
de298b1ba2
dbg
2021-09-04 22:07:55 +08:00
4dc175c966
add write_hard dataset and sampler
2021-09-04 18:47:08 +08:00
b6144fb7cf
add mix dataloader and mix sampler
2021-09-04 17:11:23 +08:00
ce39aea97f
Merge pull request #1187 from RainFrost1/retrieval_dataloader
...
fix issues when gallery == query dataset
2021-09-03 14:33:23 +08:00
50f2547005
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleClas into slim
2021-09-03 03:19:14 +00:00
d49657ad08
fix rec forward bug
2021-09-02 07:42:22 +00:00
81fcc9cb72
fix label smooth bug ( #1191 )
2021-09-01 19:36:28 +08:00
079434dc5f
feat: add AdamW
2021-09-01 08:07:48 +00:00
68c1b089e8
update slim for new trainer
2021-08-27 09:32:37 +00:00
1a1eb3a1ae
fix issues when gallery == query dataset
2021-08-27 06:25:27 +00:00
ec5e07da99
Merge pull request #1166 from Intsigstephon/develop
...
add Deephash method: DLBHC
2021-08-26 20:11:36 +08:00
d388d69a63
Update retrieval.py
2021-08-26 19:38:40 +08:00
5d1ab55af6
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleClas into slim
2021-08-26 11:30:56 +00:00
4103640884
Merge pull request #1186 from RainFrost1/trainer
...
fix loss_msg bugs
2021-08-26 17:35:26 +08:00
f61b531047
Update MV3_Large_1x_Aliproduct_DLBHC.yaml
2021-08-26 16:27:29 +08:00
c9be0fe00a
fix loss_msg bugs
2021-08-26 07:13:11 +00:00
ae768d6aee
feat: support to enable mixup and cutmix at same time
2021-08-25 11:35:11 +00:00
8e0a551359
Update deephashloss.py
2021-08-25 14:34:43 +08:00
9608c078af
Create MV3_Large_1x_Aliproduct_DLBHC.yaml
2021-08-25 14:09:21 +08:00
3de99430c0
Update deephashloss.py
2021-08-25 14:06:54 +08:00
d9ca31a694
Update deephashloss.py
2021-08-25 14:04:50 +08:00
e732d40a45
Update deephashloss.py
2021-08-25 14:00:21 +08:00
9323b1478a
Create deephashloss.py
2021-08-25 13:59:54 +08:00
52663edf60
Update retrieval.py
2021-08-25 13:57:24 +08:00
35d2be15dc
Merge branch 'PaddlePaddle:develop' into develop
2021-08-25 13:53:14 +08:00
17a06dafdb
Merge pull request #1168 from cuicheng01/develop
...
Update SwinTransformer pretrained url
2021-08-25 12:34:45 +08:00
28585e08b0
Merge pull request #1164 from RainFrost1/trainer
...
refactor trainer
2021-08-25 12:19:06 +08:00
860e4aa421
Update cosmargin.py
2021-08-24 16:20:21 +08:00
5b70d442f9
Update circlemargin.py
2021-08-24 16:19:41 +08:00
5bf74beb46
update according comments
2021-08-24 07:07:17 +00:00
8c8153e97f
Update SwinTransformer pretrained url
2021-08-24 03:22:03 +00:00
15f6f58139
refactor trainer v2
2021-08-24 03:02:55 +00:00
c9912f0a04
Update vgg_variant.py
2021-08-24 10:53:13 +08:00
34d9c8593e
Update __init__.py
2021-08-23 19:45:44 +08:00
a804bb02bd
Update VGG19_CIFAR10_DeepHash.yaml
2021-08-23 19:32:35 +08:00
0354f44574
Update metrics.py
2021-08-23 19:29:39 +08:00
2f85378bb6
Rename VGG16_CIFAR10_DeepHash.yaml to VGG19_CIFAR10_DeepHash.yaml
2021-08-23 19:23:47 +08:00
f878fb27e5
Update __init__.py
2021-08-23 19:19:19 +08:00
581af23ac6
Update VGG16_CIFAR10_DeepHash.yaml
2021-08-23 19:08:53 +08:00
26eda0efef
Update __init__.py
2021-08-23 19:08:06 +08:00
0b9f0ad001
Create vgg_variant.py
2021-08-23 19:07:35 +08:00
d963dc17da
Update VGG16_CIFAR10_DeepHash.yaml
2021-08-23 19:06:49 +08:00
865870f5f9
Update VGG16_CIFAR10_DeepHash.yaml
2021-08-23 18:53:50 +08:00
23b2332e1f
Create VGG16_CIFAR10_DeepHash.yaml
2021-08-23 18:47:03 +08:00
ebde0e13cb
refactor trainer
2021-08-22 15:10:23 +00:00
fdff2de329
fix random_erasing bug ( #1160 )
2021-08-21 17:49:49 +08:00
d21ebb85d0
fix random_erasing bug
2021-08-20 09:53:18 +00:00
4ae4a4a903
Merge pull request #1116 from weisy11/develop
...
update save sub layer result
2021-08-18 14:12:43 +08:00
9f2aec0e03
Update mobile model configs
2021-08-18 05:08:40 +00:00
9a7a377a83
Update GhostNet config
2021-08-12 08:42:07 +00:00
2940e2a9b8
Merge pull request #1130 from cuicheng01/develop
...
fix resnext101_wsl pretrain url bug
2021-08-11 23:01:13 +08:00
ac404c7a37
Update resnext101_wsl.py
2021-08-11 22:57:28 +08:00
b4678fd3fa
revert trainer
2021-08-10 11:27:56 +08:00
Wei Shengyu
gaotingquan
zhangxinyu-xyz
Walter
HydrogenSulfate
cuicheng01
cuicheng01
huangqipeng
littletomatodonkey
Bin Lu
WangChen0902
sibo2rr
Bin Lu
weishengyu
zhangbo9674
JamesLim-sy
ronnywang
Walter