提交 · f79a3a837cc162faee7c43c4cf616cbf8df706d3 · BaiXuePrincess / Paddle

22 3月, 2019 1 次提交
- S
  
  merge release/1.3 · f79a3a83
  由 sneaxiy 提交于 3月 22, 2019
  
  f79a3a83
13 2月, 2019 2 次提交
- S
  rename · 4b2794c8
  由 sneaxiy 提交于 2月 12, 2019
```
test=release/1.3
```
  4b2794c8
- S
  
  test=develop · e92defaf
  由 sneaxiy 提交于 2月 11, 2019
  
  e92defaf
30 1月, 2019 4 次提交
- C
  fix threshold_relu_op (#15594) · c4b9eac1
  由 chengduo 提交于 1月 29, 2019
```
test=develop
```
  c4b9eac1
- Y
  Return parent_idx in beam_search op (#15520) · 16d54f7f
  由 Yiqun Liu 提交于 1月 30, 2019
```
* Refine beam_search_op to output an extra parent_idx tensor.
test=develop

* Fix the unittest test_beam_search_op.
test=develop

* Fix the merging mistake.
test=develop
```
  16d54f7f
- J
  
  test=develop · e402c0ec
  由 jerrywgz 提交于 1月 30, 2019
  
  e402c0ec
- J
  
  test=develop · 334f697d
  由 jerrywgz 提交于 1月 30, 2019
  
  334f697d
29 1月, 2019 11 次提交
- D
  
  downsample -> downsample_ratio. test=develop · 733bb82e
  由 dengkaipeng 提交于 1月 29, 2019
  
  733bb82e
- D
  
  use darknet loss and trick · 577424e5
  由 dengkaipeng 提交于 1月 28, 2019
  
  577424e5
- D
  
  fix API error · af124dcd
  由 dengkaipeng 提交于 1月 14, 2019
  
  af124dcd
- T
  
  fix some typo test=develop · 20200e12
  由 tink2123 提交于 1月 10, 2019
  
  20200e12
- T
  
  add attr use_label_smooth test=develop · 2b89f590
  由 tink2123 提交于 1月 10, 2019
  
  2b89f590
- D
  
  add gtscore. test=develop · 8218e301
  由 dengkaipeng 提交于 1月 04, 2019
  
  8218e301
- D
  
  cache obj_mask and gt_match_mask. test=develop · 32d533c2
  由 dengkaipeng 提交于 12月 28, 2018
  
  32d533c2
- D
  
  ignore pred overlap gt > 0.7. test=develop · e7e4f084
  由 dengkaipeng 提交于 12月 20, 2018
  
  e7e4f084
- D
  
  remove useless code and update doc. test=develop · db8ff57a
  由 dengkaipeng 提交于 12月 17, 2018
  
  db8ff57a
- D
  
  imporve yolo loss implement. test=develop · 0c4acc83
  由 dengkaipeng 提交于 12月 16, 2018
  
  0c4acc83
- D
  
  use stable Sigmoid Cross Entropy implement. test=develop · 192d2938
  由 dengkaipeng 提交于 12月 06, 2018
  
  192d2938
28 1月, 2019 2 次提交
- J
  
  remove inplace arg, test=develop · aaf75627
  由 jerrywgz 提交于 1月 28, 2019
  
  aaf75627
- T
  add align_flag · a0c63f11
  由 tink2123 提交于 1月 27, 2019
```
test=develop
```
  a0c63f11
25 1月, 2019 3 次提交
- T
  modified default parameters · b64cdaf6
  由 tink2123 提交于 1月 25, 2019
```
test=develop
```
  b64cdaf6
- J
  
  refine code, test=develop · 466a10dc
  由 jerrywgz 提交于 1月 25, 2019
  
  466a10dc
- J
  
  add attr variance for box coder, test=develop · a39240c3
  由 jerrywgz 提交于 1月 25, 2019
  
  a39240c3
24 1月, 2019 5 次提交

Add the CUDA kernel for beam_search op (#15020) · 3008fa12

由 Yiqun Liu 提交于 1月 24, 2019

* Refine the beam_search op and test.

* A basic CUDA implementation of beam_search for small batch_size.

* Implement CUDA kernel for beam_search_op.

* Use multiple CUDA threads in the same block to select the top beam.

* Update the python api of beam_search op.

* Enable extend function in CPU kernel of beam_search op.

* Unify the CUDA codes.
test=develop

* Unify the CPU kernel of beam_search op.

* Ensure the seletced items of beam_search_op's CPU kernel sorted by scores.

* Update the description of beam_search in API.spec.

* Enable the use of CUDA kernel in beam_search op.

* Exclude the beam_search's CUDA unittest when there is no CUDA gpu, and delete some debuging statements.
test=develop

* Follow comments.
test=develop

* Call the CPU kernel for beam_search op when batch_size > 4.
test=develop

* Remove the except of is_empty op in PrepareData.
test=develop

3008fa12

T
modified some comments · 78145c7d
由 tink2123 提交于 1月 24, 2019
```
test=develop
```
78145c7d
T
nce add check sample lables, test=develop (#15463) · 5cfc40de
由 tangwei12 提交于 1月 24, 2019
```
* nce add check sample lables, test=develop
```
5cfc40de
T
modified some comments · e448bdb2
由 tink2123 提交于 1月 24, 2019
```
test=develop
```
e448bdb2
T
fixed some errors · 88744e4a
由 tink2123 提交于 1月 24, 2019
```
test=develop
```
88744e4a

23 1月, 2019 4 次提交
- T
  add align_corners and align_mode for image_resize · 48cc4846
  由 tink2123 提交于 1月 23, 2019
```
test=develop
```
  48cc4846
- J
  
  refine code, test=develop · 11f1baa4
  由 jerrywgz 提交于 1月 23, 2019
  
  11f1baa4
- J
  
  add comment and refine code, test=develop · cc534530
  由 jerrywgz 提交于 1月 23, 2019
  
  cc534530
- Q
  Add generate_mask_labels_op to support Mask-RCNN and refine some code. (#15371) · 07dc5a15
  由 qingqing01 提交于 1月 23, 2019
```
* Add generate_mask_labels_op to support Mask-RCNN.
* Refine sigmoid_cross_entropy to support nomalize mode.
* Fix generator_proposals_label.
* Use DeviceTemporaryAllocator in roi_pool and roi_algin.
* Remove shape check in data_feeder.
```
  07dc5a15
22 1月, 2019 3 次提交
- J
  
  refine comment and unittest, test=develop · c12a969b
  由 jerrywgz 提交于 1月 22, 2019
  
  c12a969b
- J
  
  add gpu kernel for box clip, test=develop · 1c558ad3
  由 jerrywgz 提交于 1月 22, 2019
  
  1c558ad3
- Q
  
  add NumpyArrayInitializer and use it to refactor nce op · a1326cf3
  由 Qiao Longfei 提交于 1月 22, 2019
  
  a1326cf3
21 1月, 2019 1 次提交

Memory optimization of depthwise conv op and group norm op (#15313) · 9f8f0fc2

由 Dun 提交于 1月 21, 2019

* mem opt

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* refine code  test=develop

* refine code  test=develop

* refine code  test=develop

* refine code  test=develop

* refine with cub test=develop

* fix mkldnn test && remove comments && test=develop

* polish code && test=develop

* add only_forward test && test=develop

9f8f0fc2

18 1月, 2019 2 次提交

J

add nms api · b62a17bb
由 jerrywgz 提交于 1月 18, 2019

b62a17bb

Tree conv op (#15217) · e2ba9668

由 zhaozhehao 提交于 1月 18, 2019

* refactor tree2col operator with new memory mechanism test=develop

* test=develop

* test=develop

* Modified API according to panyx0718 test=develop

* fix API change according to heavengate test=develop

* Modify API comment test=develop

e2ba9668

17 1月, 2019 1 次提交
- J
  
  add axis for box coder op · 10dd3b37
  由 jerrywgz 提交于 1月 17, 2019
  
  10dd3b37
16 1月, 2019 1 次提交
- M
  
  Add single GPU support to imperative · 315b133e
  由 minqiyang 提交于 1月 16, 2019
  
  315b133e

BaiXuePrincess / Paddle 与 Fork 源项目一致

BaiXuePrincess / Paddle
与 Fork 源项目一致