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
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
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
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
97398d9f12
fix export pretrained_model when it is None
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
6cc6540ca5
add different seed for workers and replicas
2022-11-24 11:51:13 +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
7ff257ea69
fix random seed bug for pksampler in DDP
2022-11-22 16:47:47 +08:00
cddc899f34
fix dataloader next
2022-11-09 19:01:00 +08:00
7d9f4dcb59
change Tensor.numpy()[0] to float(Tensor) for 0-D tensor case
2022-11-01 14:37:11 +08:00
0cec70bd22
[CustomDevice]add support for custom NPU, test=develop
2022-10-26 10:33:10 +08:00
944763d7a5
add fixmatch
2022-10-25 12:04:22 +08:00
09200a31f4
remove redundant code, fix bugs in lr.step, merge GoodsDataset into Vehicle
2022-10-19 07:18:21 +00:00
2cfd8dd828
add xbm
2022-10-17 15:45:45 +08:00
61b4153907
add batch Tensor collate to simplify dali code in train/eval/retrival code
2022-10-13 12:05:50 +08:00
50fc7d0eae
fix bugs to adapt to the new framework
2022-09-20 10:06:20 +00:00
cc46db1586
fix bugs to adapt to the new framework
2022-09-19 02:01:31 +00:00
0b9f62262a
Merge branch 'develop' into fix_multilabel
2022-09-14 14:41:32 +08:00
c03a66bfe4
Rename variable names that may be confused in retrieval.py
2022-08-26 06:16:11 +00:00
5a4874079d
fix some bugs
2022-08-23 10:59:30 +00:00
1b5e00e82a
add PP-ShiTuV2 code
2022-08-23 07:54:58 +00:00
eade1b7232
fix multilabel
2022-08-22 06:40:26 +00:00
436f64ad84
Merge branch 'develop' into ConvNeXt
2022-07-09 21:50:31 +08:00
266db4d89c
fix classification bug
2022-07-06 20:38:40 +08:00
e8fc16d76b
update rep condition
2022-06-28 05:58:14 +00:00
de1e9cab74
update pact chain
2022-06-28 04:06:54 +00:00
43410aa852
update config, add amp eval for retrieval
2022-06-21 23:03:56 +08:00
794af8c06f
add kd doc ( #1997 )
...
* add kd doc
* fix
* add ssld doc
* fix ssld
* fix ssld
* Update knowledge_distillation.md
* fix doc
* fix dist export
* fix
* add dist doc
* fix speed info
* Update ssld.md
* Update ssld.md
2022-06-09 14:52:50 +08:00
b457c393eb
fix: dbg ( #1993 )
...
1. config["Metric"]["Train"] may be None
2. fliter -> list
2022-06-07 20:08:48 +08:00
80358efbe2
fix: pop TopkAcc when using batch_transform_ops
2022-06-06 16:47:57 +08:00
ccefbd7864
fix: dbg
2022-06-06 16:47:57 +08:00
df3e75dde4
fix: warn when topk parameter setting is wrong
2022-06-06 16:47:57 +08:00
4003cdb7ad
add traffic sign yaml ( #1966 )
...
* add traffic sign and vehicle attr doc and yaml
2022-06-06 13:13:50 +08:00
d039691fce
Merge pull request #1963 from TingquanGao/dev/rm_fluid
...
remove fluid
2022-06-06 10:54:16 +08:00
ad71254e68
Merge pull request #1960 from zhiboniu/dev_attr
...
support attribute infer
2022-05-27 19:22:17 +08:00
dcef409dde
Merge branch 'develop' into adaface
2022-05-27 14:19:03 +08:00
c22bdc7e54
remove fluid
2022-05-26 07:40:15 +00:00
a4e1da6610
modify attr export model
2022-05-25 08:13:38 +00:00
4091592cfb
Merge pull request #1917 from zhiboniu/develop
...
add attribute support
2022-05-25 10:19:21 +08:00
6dac07f68d
fix quant logic ( #1941 )
...
* fix quant logic
* add support for trt+int8 inference
* add support for swin quant
* fix swin and quant
* fix assert info
* fix assert info
* fix log
2022-05-23 19:04:27 +08:00
edf1129e5d
match new eval function
2022-05-23 10:27:55 +00:00
699c10aaeb
Merge remote-tracking branch 'ppcls/develop' into develop
2022-05-23 08:03:46 +00:00
8f5fe61540
Merge pull request #1925 from cuicheng01/add_person_demo
...
Add person demo
2022-05-23 09:26:49 +08:00
683adcda46
fix: support AMP infer
2022-05-18 18:10:44 +08:00
e4327c8686
log tip when export succeeded
2022-05-18 13:00:00 +08:00
05ecf1d045
multi-card eval support
2022-05-18 04:54:44 +00:00
50900443f3
remove strongbaseline_attr, etc...
2022-05-18 04:54:43 +00:00
26d5b7d1cc
adapted dataset and loss
2022-05-18 04:54:43 +00:00
0a3ecf60b4
add attribute strongbaseline
2022-05-18 04:54:43 +00:00
afafb8f41d
fix save load
2022-05-17 13:24:24 +00:00
32c99be6aa
add adaface
2022-05-16 03:50:35 +00:00
43d1eba917
Merge branch 'develop' into add_re_ranking
2022-05-16 11:04:32 +08:00
45b1296c25
Add cls_demo_person code
2022-05-14 09:31:52 +00:00
f04b52343f
fix: unable to export rep net
2022-05-14 14:13:25 +08:00
565053167d
update code
2022-05-11 18:57:16 +08:00
88295413f5
add re-ranking code
2022-05-11 17:33:07 +08:00
e61f392598
Merge branch 'develop' into ConvNeXt
2022-05-09 12:22:37 +08:00
a618534ebc
fix log_info
2022-05-09 11:51:26 +08:00
56b8710dc4
fix: fix bug get paddle version
2022-05-06 19:51:44 +08:00
7283598041
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleClas into adaface
2022-05-06 04:50:31 +00:00
bdc535bb39
add adaface
2022-05-06 04:50:26 +00:00
bd524e8a88
Merge pull request #1819 from weisy11/reid
...
复现reid-strong-baseline
2022-05-06 12:05:07 +08:00
4bc4b7e0e2
Merge pull request #1876 from TingquanGao/dev/fix_amp_eval
...
fix: amp eval
2022-05-05 20:39:02 +08:00
1c31010b14
refine code
2022-05-05 20:28:59 +08:00
16f910b451
add m1 and baseline config
2022-05-05 19:55:08 +08:00
0b1481402b
merge devevelop
2022-05-05 14:42:06 +08:00
b334da6fad
Merge branch 'develop' into ConvNeXt
2022-05-05 14:40:46 +08:00
bb13f3c4f5
fix single card dist ( #1889 )
...
* fix single card logit
* fix distillation yaml files
2022-05-05 09:48:56 +08:00
275945dff9
fix: compatible with Paddle 2.2, 2.3, and develop.
2022-04-29 10:21:09 +00:00
24372cc6e5
update: update the default gpu num to 8 when using AdamW
2022-04-29 17:31:12 +08:00
8b8a02d607
add update_freq option for gradient accumulation
2022-04-28 00:50:28 +08:00
ed8202236b
add EMA code
2022-04-28 00:39:53 +08:00
59a3dcfc1c
fix: amp eval
2022-04-26 12:26:17 +00:00
fea9522a69
fix: dbg
2022-04-26 12:07:59 +08:00
97e8abc3db
refine code and yaml
2022-04-24 14:38:26 +08:00
4e6c36e269
Merge pull request #1833 from TingquanGao/dev/fix_dist_loss
...
fix calc metric error and calc loss error in distributed.
2022-04-22 22:41:57 +08:00
b86ddf470e
fix: when eval only, AMP can be enabled
2022-04-22 17:49:44 +08:00
b5a7eea504
fix: fix the bug that DistributedBatchSampler may sample repeatedly
2022-04-22 09:39:22 +00:00
15a0afc67c
update code
2022-04-22 15:52:16 +08:00
bc6e7f5cf5
update code
2022-04-22 15:26:05 +08:00
9dde9376fb
update code
2022-04-22 15:25:11 +08:00
15997ea9d0
update code
2022-04-22 12:03:17 +08:00
f2982e5e47
update code
2022-04-22 12:01:05 +08:00
17fd1bc2c0
refine code
2022-04-22 12:00:03 +08:00
aa26a8c1d8
fix bug for static graph
2022-04-21 16:31:28 +08:00
daf7eea23d
fix code
2022-04-21 15:43:53 +08:00
dfd7749828
refine hard code
2022-04-21 14:37:00 +08:00
41e1a86caf
add center loss
2022-04-21 00:17:54 +08:00
e6feb68bb8
Merge pull request #1824 from TingquanGao/dev/spt_amp_eval
...
fix: fp32 eval by default when enable amp
2022-04-20 14:40:46 +08:00
3a1276d315
train_loss_func only used in train mode
2022-04-19 19:54:48 +08:00
24abea151a
support for multi optimizer case
2022-04-19 14:26:42 +08:00
83ed5195c3
fix: set use_fp16_test to True when AMP O2 is enabled
2022-04-18 06:14:43 +00:00
1789da6422
fix bug
2022-04-18 11:26:32 +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
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
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
a944603da0
fix log twice bug
2022-03-30 08:31:35 +00:00
b62b98d79f
feat: support mlu device and amp of mlu
2022-03-14 15:48:26 +08:00
f68c098a4a
fix train acc log
2022-03-09 19:58:36 +08:00
7595ba6d70
add AFD ( #1683 )
...
* add AFD
2022-02-28 19:11:50 +08:00
dc6281a6d4
add benchmark for tipc
2022-02-10 08:25:52 +00:00
42134cd8dd
fix: raise warning when using Global.class_num
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
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
aea712cc87
add dist of rec model ( #1574 )
...
* add distillation loss func and rec distillation
2022-01-05 19:25:36 +08:00
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
7da2a997e9
fix: save latest model every epoch
2021-12-27 22:04:26 +08:00
5d53e9f152
fix: raise warning when setting batch_transform_ops and TopkAcc
2021-12-24 21:22:52 +08:00
28061f537c
refine optimizer init logice
2021-12-21 06:28:13 +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
534037d145
dbg
2021-12-10 11:14:14 +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
a3b54f15d5
fix export quant_model
2021-12-03 07:39:31 +00:00
f7ccc874e2
fix dali distributed eval bug
2021-11-16 11:09:21 +08:00
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
ed459a2a16
refactor: adapt to static graph in deprecating MixCELoss
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
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
zh-hike
HydrogenSulfate
zengshao0622
USTCKAY
dongshuilong
cuicheng01
cuicheng01
Yang Nie
littletomatodonkey
Tingquan Gao
Wei Shengyu
zhiboniu
Yang Nie
huangqipeng
WangChen0902
zhangbo9674
weishengyu
stephon
ronnywang