提交 · 34988bf23b7bc0c048ef94f88644bdb0def29a33 · PaddlePaddle / models

11 4月, 2019 2 次提交
- L
  
  mark loss as persistable · a6437859
  由 liuwei1031 提交于 4月 11, 2019
  
  a6437859
- L
  
  manually enable memory optimize for object_detection · fb5fa1af
  由 liuwei1031 提交于 4月 11, 2019
  
  fb5fa1af
04 4月, 2019 1 次提交

Adjust whole models structure (#1979) · 43cdafbb

由 Yibing Liu 提交于 4月 04, 2019

* Shift up fluid models

* Update nlp submodules

* Add redirect guide in org readme

* Move HiNAS_models to AutoDL

43cdafbb

02 2月, 2019 1 次提交
- Q
  Revert pr1732 (#1741) · c1c5ed64
  由 qingqing01 提交于 2月 02, 2019
```
* Delete file
* Rever the raw file
```
  c1c5ed64
01 2月, 2019 1 次提交

Adjust the structure of whole repo (#1732) · 0eda9630

由 Yibing Liu 提交于 2月 01, 2019

* Adjust the structure of whole repo

* Correct the readme for speec

* Update submodules LAC, Senta and SimNet

0eda9630

28 1月, 2019 1 次提交
- Q
  
  Remove some unused variable. (#1706) · 0a268ea1
  由 qingqing01 提交于 1月 28, 2019
  
  0a268ea1
24 1月, 2019 1 次提交

Refine code and fix some model. (#1693) · a742f5c6

由 qingqing01 提交于 1月 24, 2019

* Fix exeception when finishing training in detection.
* Fix fluid.Trainer in HiNAS_models.
* Remove coco doc in SSD detection.

a742f5c6

30 10月, 2018 1 次提交
- Q
  Quantization-aware training for SSD. (#1409) · 372d4d14
  由 qingqing01 提交于 10月 30, 2018
```
* Quantization-aware training for SSD.
* Clean code and refine doc.
```
  372d4d14
29 10月, 2018 1 次提交
- Q
  
  Aggregate CV models (#1400) · 58e9bc20
  由 qingqing01 提交于 10月 29, 2018
  
  58e9bc20
16 10月, 2018 1 次提交
- X
  
  fix model to use different names for train and test so that var name don't conflict · 57932ed5
  由 Xin Pan 提交于 10月 16, 2018
  
  57932ed5
28 9月, 2018 1 次提交
- Q
  
  Support Python3 for face detection evalutation (#1319) · 6e239c97
  由 qingqing01 提交于 9月 28, 2018
  
  6e239c97
26 9月, 2018 1 次提交
- Q
  
  Fix args. (#1298) · 8d4ccb19
  由 qingqing01 提交于 9月 26, 2018
  
  8d4ccb19
18 9月, 2018 1 次提交
- B
  Use pyreader in face detection model (#1183) · 97574429
  由 Bai Yifan 提交于 9月 18, 2018
```
* add pyreader
```
  97574429
12 9月, 2018 1 次提交
- B
  some fix about CE (#1242) · 31e2fd99
  由 Bai Yifan 提交于 9月 12, 2018
```
* ce fix
```
  31e2fd99
10 9月, 2018 1 次提交
- B
  Fix object detection reader (#1219) · 258ae207
  由 Bai Yifan 提交于 9月 10, 2018
```
* Accelerate reader in object_detection.
```
  258ae207
02 9月, 2018 1 次提交
- B
  Revert reader (#1216) · 3984c24b
  由 Bai Yifan 提交于 9月 02, 2018
```
* revert reader
```
  3984c24b
29 8月, 2018 2 次提交
- B
  
  fix ce · 654b535a
  由 baiyfbupt 提交于 8月 29, 2018
  
  654b535a
- B
  
  update ce · 92c166fd
  由 baiyfbupt 提交于 8月 29, 2018
  
  92c166fd
27 8月, 2018 1 次提交
- B
  Object_detection reader accelerate (#1177) · 09291452
  由 Bai Yifan 提交于 8月 27, 2018
```
* object_detection accelerate
```
  09291452
17 8月, 2018 1 次提交
- B
  Refine ce support for object detection (#1165) · 96469e70
  由 Bai Yifan 提交于 8月 17, 2018
```
* update ce
```
  96469e70
13 8月, 2018 1 次提交
- M
  
  Port object_detection to Python3 · 3d021fb2
  由 minqiyang 提交于 8月 13, 2018
  
  3d021fb2
09 8月, 2018 1 次提交
- B
  
  fix tab (#1117) · 776514b3
  由 Bai Yifan 提交于 8月 09, 2018
  
  776514b3
08 8月, 2018 2 次提交
- B
  
  add 4card kpis · c458e198
  由 baiyfbupt 提交于 8月 08, 2018
  
  c458e198
- B
  
  kpi fix · edc6b362
  由 baiyfbupt 提交于 8月 08, 2018
  
  edc6b362
07 8月, 2018 1 次提交
- B
  
  update ce · f35daf3e
  由 baiyfbupt 提交于 8月 07, 2018
  
  f35daf3e
06 8月, 2018 3 次提交
- B
  
  model ce · 2a1124c6
  由 baiyfbupt 提交于 8月 06, 2018
  
  2a1124c6
- B
  
  update ce kpi · a85a6014
  由 baiyfbupt 提交于 8月 06, 2018
  
  a85a6014
- B
  
  add ce · 35f9269a
  由 baiyfbupt 提交于 8月 06, 2018
  
  35f9269a
26 7月, 2018 1 次提交
- B
  Add ce run.sh scripts (#1072) · a56d95e6
  由 baiyf 提交于 7月 26, 2018
```
* add ce run.sh
```
  a56d95e6
20 6月, 2018 1 次提交
- X
  Update SSD documentation (#987) · 3257b64c
  由 Xingyuan Bu 提交于 6月 20, 2018
```
* Refine documentation and code.
```
  3257b64c
13 6月, 2018 1 次提交
- X
  Update SSD documentation. (#968) · 3aa16d52
  由 Xingyuan Bu 提交于 6月 13, 2018
```
* update wiki

* refine wiki

* train.py default args

* update wiki cn

* update wiki
```
  3aa16d52
22 5月, 2018 1 次提交
- Q
  PyramidBox for face detection. (#921) · c2ed053c
  由 qingqing01 提交于 5月 22, 2018
```
* PyramidBox for face detection.

* Update some hyper parameters.

* Update pyramidbox.py
```
  c2ed053c
17 5月, 2018 1 次提交
- X
  
  epocs typo (#919) · 1cbbddd8
  由 Xingyuan Bu 提交于 5月 17, 2018
  
  1cbbddd8
11 5月, 2018 1 次提交
- X
  Hotfix paralle nccl args (#903) · 6296090d
  由 Xingyuan Bu 提交于 5月 11, 2018
```
* fix parallel

* typo

* fix data best_map parameter bug
```
  6296090d
27 4月, 2018 2 次提交

COCO dataset for SSD and update README.md (#844) · c92deba1

由 Xingyuan Bu 提交于 4月 27, 2018

* ready to coco_reader

* complete coco_reader.py & coco_train.py

* complete coco reader

* rename file

* use argparse instead of explicit assignment

* fix

* fix reader bug for some gray image in coco data

* ready to train coco

* fix bug in test()

* fix bug in test()

* change coco dataset to coco2017 dataset

* change dataset from coco to coco2017

* change learning rate

* fix bug in gt label (category id 2 label)

* fix bug in background label

* save model when train finished

* use coco map

* adding coco year version args: 2014 or 2017

* add coco dataset download, and README.md

* fix

* fix image truncted IOError, map version error

* add test config

* add eval.py for evaluate trained model 

* fix

* fix bug when cocoMAP

* updata READEME.md

* fix cocoMAP bug

* find strange with test_program = fluid.default_main_program().clone(for_test=True)

* add inference and visualize, awa, README.md

* upload infer&visual example image

* refine image

* refine

* fix bug after merge

* follow yapf

* follow comments

* fix bug after separate eval and eval_cocoMAP

* follow yapf

* follow comments

* follow yapf

* follow yapf

c92deba1

COCO dataset for SSD and update README.md (#844) · 496ff37b

由 Xingyuan Bu 提交于 4月 27, 2018

* ready to coco_reader

* complete coco_reader.py & coco_train.py

* complete coco reader

* rename file

* use argparse instead of explicit assignment

* fix

* fix reader bug for some gray image in coco data

* ready to train coco

* fix bug in test()

* fix bug in test()

* change coco dataset to coco2017 dataset

* change dataset from coco to coco2017

* change learning rate

* fix bug in gt label (category id 2 label)

* fix bug in background label

* save model when train finished

* use coco map

* adding coco year version args: 2014 or 2017

* add coco dataset download, and README.md

* fix

* fix image truncted IOError, map version error

* add test config

* add eval.py for evaluate trained model 

* fix

* fix bug when cocoMAP

* updata READEME.md

* fix cocoMAP bug

* find strange with test_program = fluid.default_main_program().clone(for_test=True)

* add inference and visualize, awa, README.md

* upload infer&visual example image

* refine image

* refine

* fix bug after merge

* follow yapf

* follow comments

* fix bug after separate eval and eval_cocoMAP

* follow yapf

* follow comments

* follow yapf

* follow yapf

496ff37b

23 4月, 2018 1 次提交
- Q
  
  Support training with single device. (#869) · 5d1dc2ff
  由 qingqing01 提交于 4月 23, 2018
  
  5d1dc2ff
17 4月, 2018 1 次提交
- D
  
  Follow comments. · e32d3349
  由 Dang Qingqing 提交于 4月 17, 2018
  
  e32d3349
16 4月, 2018 2 次提交
- D
  
  Update argument comments. · 19f9260b
  由 Dang Qingqing 提交于 4月 16, 2018
  
  19f9260b
- D
  
  Refine reader.py and train.py · e76927fe
  由 Dang Qingqing 提交于 4月 16, 2018
  
  e76927fe

PaddlePaddle / models 大约 2 年 前同步成功

PaddlePaddle / models
大约 2 年前同步成功