c2aed7c0a6
fix add order ( #493 )
2020-12-17 11:46:20 +08:00
1da9fdf379
Fix GoogleNet to GoogLeNet ( #492 )
2020-12-17 11:20:41 +08:00
fdfce2d6d5
add kunlun readme ( #489 )
...
* add kunlun readme
2020-12-16 20:58:26 +08:00
d80d53f955
fix resnest ( #490 )
2020-12-16 19:03:11 +08:00
bcaf6a8528
fix trt doc ( #485 )
...
* fix trt doc
* update history
2020-12-16 12:01:32 +08:00
3d5cde1aed
Update main.cpp
2020-12-15 22:54:20 +08:00
13e8fcdc43
fix cpp time ( #483 )
...
* fix cpp time
* fix time
2020-12-15 21:55:02 +08:00
cf68eafa56
add cpp trt ( #480 )
2020-12-15 19:22:13 +08:00
8fd56a4503
fix static train ( #478 )
2020-12-15 16:43:15 +08:00
29b305d228
add profile for pred ( #476 )
2020-12-15 14:32:07 +08:00
d860430b55
Fix some description of documentations ( #473 )
...
Fix some description of documentations
2020-12-14 21:43:45 +08:00
a463b0a2dc
fix model cnt ( #469 )
2020-12-14 16:00:04 +08:00
bb95b5bd9c
Update quick_start.md
2020-12-13 21:25:34 +08:00
e8b3be1053
Update getting_started.md
2020-12-13 21:24:57 +08:00
b68ca02b65
Adapt to the develop version paddle_inference on Win32 and Linux ( #468 )
2020-12-13 14:21:29 +08:00
2843bd877a
Update models_intro_en.md
2020-12-12 11:58:17 +08:00
46f8676580
Update models_intro.md
2020-12-12 11:56:36 +08:00
dc3020ab4a
support fp16 training ( #435 )
...
* support fp16 training
* Use compiled training program
* Change timing ips.
* Use dali
* add pure fp16 training
* fix a bug, which will not use fuse pass using pure fp16 training.
* modify code as review
* modify loss, so that it will use different loss when using pure fp16 training.
* remove some fluid API
* add static optimizer.
2020-12-11 11:04:51 +08:00
9992415867
add mkldnn speed problm ( #465 )
2020-12-11 00:39:12 +08:00
b9d243f854
Update utils.py
2020-12-11 00:24:14 +08:00
15b18973f1
fix eval script ( #464 )
...
* fix eval script
* fix dali shell
2020-12-10 23:45:58 +08:00
e3801c5515
Fix the bug about calling create_predictor repeatedly in hubserving ( #462 )
2020-12-10 01:15:24 +08:00
022a4114d6
Update faq_series.md
2020-12-09 20:11:58 +08:00
9bc00143a3
Update README_cn.md
2020-12-09 20:11:17 +08:00
b2baeab8d7
Add FAQ 20201207 ( #459 )
...
* Add FAQ 20201207
* Fix FAQ20201207
2020-12-09 20:10:29 +08:00
066d53f8ec
support cpu/xpu/gpu in static graph ( #460 )
2020-12-08 20:59:23 +08:00
1839105f27
fix resnest ( #458 )
2020-12-08 18:47:46 +08:00
a76e404d9c
fix time sta ( #457 )
2020-12-08 17:05:00 +08:00
a73573a346
Add se_hrnet_w64_c_ssld_pretrained ( #452 )
...
add se hrnet64_c
2020-12-06 17:52:34 +08:00
1ecf8334ff
fix pred ( #450 )
...
* fix pred
* fix resnest
* fix hrnet se
* fix se for export
2020-12-06 03:08:44 +08:00
0df5ba63df
Update test_hubserving.py
2020-12-04 10:43:56 +08:00
049cbb26d7
Update run_dali.sh
2020-12-03 15:58:07 +08:00
1e4925704d
fix dali train ( #446 )
2020-12-03 15:48:35 +08:00
46dfc57e2a
update kunlun epoch num ( #445 )
2020-12-03 14:06:13 +08:00
e92cb0b93c
fix init model in static mode ( #444 )
2020-12-03 12:50:33 +08:00
fff2a92b25
add shell scripts to run training on single node and multiple nodes. ( #424 )
...
* add shells, test=develop
2020-12-03 11:11:39 +08:00
2b77c71459
Support DALI ( #442 )
2020-12-02 22:06:23 +08:00
c0b73558b1
Add files via upload
2020-12-02 20:09:49 +08:00
38b89b34ef
Delete joinus.png
2020-12-02 20:09:12 +08:00
832364e191
support static graph train for kunlun ( #441 )
2020-12-02 18:36:51 +08:00
8e5bde6c39
Update predict.py
2020-12-01 01:20:10 +08:00
07330e0e42
fix resnest typo ( #380 )
...
fix resnest, ghostnet typo
2020-11-30 12:52:58 +08:00
96c078dafc
fix download link ( #432 )
...
* fix download link
2020-11-30 12:43:05 +08:00
91785a45e1
fix dpn ( #430 )
...
* fix dpn
* fix se resnext101 metrics
2020-11-29 18:10:20 +08:00
68be3ab288
Fix some minor bugs to adapt to paddle2.0rc. ( #431 )
...
* Update mobilenet_v3.py
* Update densenet.py
* Update resnest.py
* Update hrnet.py
* Update vgg.py
* Update xception.py
2020-11-29 18:09:48 +08:00
6796bca110
fix logger ( #426 )
2020-11-25 19:45:43 +08:00
18840f1f88
Add GhostNet_x1_3_ssld_pretrained in dygraph branch. ( #419 )
...
add GhostNet_x1_3_ssld_pretrained
2020-11-24 10:14:02 +08:00
6abaa0c810
fix dpn ( #416 )
2020-11-21 17:46:53 +08:00
463980f331
add support for multi cards eval ( #413 )
...
* add support for multi cards eva
2020-11-20 18:10:06 +08:00
6be63583e4
Update data_en.md
2020-11-20 11:23:31 +08:00
littletomatodonkey
Tingquan Gao
QingshuChen
huangxu96
QingshuChen
cuicheng01
lilong12