提交 · f4e6fe078629389a67761b120c15e7c1027da2c3 · PaddlePaddle / PaddleDetection

24 10月, 2018 1 次提交

由 qingqing01 提交于 10月 24, 2018

1. Fix CUDA kernel when height is large than 2048.
2. Support input with more than 2D.
3. Fix unit test when k is large than 1.
4. Enhence unit testing.

test=develop

c7379a73

23 10月, 2018 4 次提交
- C
  Refine Split op (#13967) · a7497653
  由 chengduo 提交于 10月 23, 2018
```
* speedup split_op
test=develop

* speedup split_op
test=develop

* rename ConcatGrad to Split

* refine concat and split
test=develop

* fix compile error
```
  a7497653
- J
  
  refine code · e0708e62
  由 jerrywgz 提交于 10月 23, 2018
  
  e0708e62
- T
  fix typo and warning in analyzer_resnet50_test · 316bc9bf
  由 Tao Luo 提交于 10月 23, 2018
```
test=develop
```
  316bc9bf
- J
  
  fix rpn target assign test=develop · f06c6193
  由 jerrywgz 提交于 10月 23, 2018
  
  f06c6193
22 10月, 2018 2 次提交
- X
  clean up after the changes have been stopped for so long. · 8f2116d8
  由 Xin Pan 提交于 10月 18, 2018
```
test=develop
```
  8f2116d8
- G
  Add rpc profiler flags. (#13989) · 58c027cc
  由 gongweibao 提交于 10月 22, 2018
```
Add rpc profiler flags
```
  58c027cc
21 10月, 2018 7 次提交
- D
  Refine doc for generate_proposals_op. · 56936b9e
  由 Dang Qingqing 提交于 10月 20, 2018
```
test=develop
```
  56936b9e
- T
  MKLDNN conv + elementwise_add fusion: skip connection attribute renamed.... · 4be45af1
  由 Tomasz Patejko 提交于 9月 27, 2018
```
MKLDNN conv + elementwise_add fusion: skip connection attribute renamed. Comments about patterns added.

test=develop
```
  4be45af1
- M
  MKLDNN conv + elementwise_add fusion: Fix output_data to point to the right... · f6881971
  由 Michal Gallus 提交于 9月 25, 2018
```
MKLDNN conv + elementwise_add fusion: Fix output_data to point to the right tensor, also fix transpiler integration
```
  f6881971
- T
  
  MKLDNN conv + elementwise_add fusion: further reformatting · bf95ac36
  由 Tomasz Patejko 提交于 9月 19, 2018
  
  bf95ac36
- T
  
  MKLDNN conv + elementwise_add fusion: parameter name changed to ResidualData · b8e54ab5
  由 Tomasz Patejko 提交于 9月 18, 2018
  
  b8e54ab5
- T
  MKLDNN conv + elementwise_add fusion: output and elemwise param share data in... · 41f3d78f
  由 Tomasz Patejko 提交于 9月 17, 2018
```
MKLDNN conv + elementwise_add fusion: output and elemwise param share data in conv primitive. Output is properly allocated
```
  41f3d78f
- T
  
  MKLDNN conv + elementwis_add fusion: initial work on passing eltwise data to conv primitive · 56528531
  由 Tomasz Patejko 提交于 9月 17, 2018
  
  56528531
19 10月, 2018 5 次提交
- T
  
  refine and add seqconv elementwiseadd relu op test · 339e655a
  由 tensor-tang 提交于 10月 19, 2018
  
  339e655a
- D
  Fix unit test · 8e0b9496
  由 Dang Qingqing 提交于 10月 19, 2018
```
test=develop
```
  8e0b9496
- Y
  Ocr end2end dev (#13889) · fcb2e810
  由 Yipeng 提交于 10月 19, 2018
```
* add detect and end2end code

* update the scale for coodinates restore

* fix merge bug with dev.

* fix merge bug with dev.

* test=develop

* fix code style test=develop

* fix code style test=develop

* test=develop

* test=develop

* test=develop
```
  fcb2e810
- T
  
  refine and add eltadd_relu unit test · e5ce9659
  由 tensor-tang 提交于 10月 19, 2018
  
  e5ce9659
- T
  
  fuse elementwise_add and relu · 7cb19a59
  由 tensor-tang 提交于 10月 19, 2018
  
  7cb19a59
18 10月, 2018 10 次提交
- T
  
  init seqconv eltadd relu op · 3c249283
  由 tensor-tang 提交于 10月 18, 2018
  
  3c249283
- J
  
  test=develop · 55334262
  由 jerrywgz 提交于 10月 18, 2018
  
  55334262
- J
  
  test=develop · 9a14ca91
  由 jerrywgz 提交于 10月 18, 2018
  
  9a14ca91
- G
  Add grpc error context. (#13957) · a831ecc7
  由 gongweibao 提交于 10月 18, 2018
```
Add grpc error context
```
  a831ecc7
- Q
  Add affine channel op to speed and save memory for faster-rcnn model. (#13919) · 67a2b521
  由 qingqing01 提交于 10月 18, 2018
```
* Add affine channel op.
* Update code and add Python API.
test=develop
* Update API.spec
test=develop
```
  67a2b521
- T
  
  clean code exp avx · 74843558
  由 tensor-tang 提交于 10月 18, 2018
  
  74843558
- T
  
  fix illegal instruction of rnn2 · b4751a34
  由 tensor-tang 提交于 10月 18, 2018
  
  b4751a34
- T
  
  fix illegal instruction of rnn1 and text · 36588b33
  由 tensor-tang 提交于 10月 18, 2018
  
  36588b33
- G
  Add rpc timeline. (#13900) · 078223b3
  由 gongweibao 提交于 10月 18, 2018
```
Add rpc timeline
```
  078223b3
- Q
  
  Small changes for sum_op to avoid zero setting. (#13923) · 5dbb2e99
  由 qingqing01 提交于 10月 18, 2018
  
  5dbb2e99
17 10月, 2018 9 次提交
- T
  
  fix some compiler warning · e47f4186
  由 Tao Luo 提交于 10月 17, 2018
  
  e47f4186
- D
  
  fix compile in cpu error. test=develop · 00e8791f
  由 dzhwinter 提交于 10月 17, 2018
  
  00e8791f
- T
  fix warning and mac compile · e69328c3
  由 tensor-tang 提交于 10月 17, 2018
```
test=develop
```
  e69328c3
- D
  
  use binary search. test=develop · d239cf2e
  由 dzhwinter 提交于 10月 17, 2018
  
  d239cf2e
- D
  
  use binary search. test=develop · a9f5f822
  由 dzhwinter 提交于 10月 17, 2018
  
  a9f5f822
- N
  Add ceil model pooling for trt (ocr attention) · 2b5edfbc
  由 nhzlx 提交于 10月 17, 2018
```
test=develop
```
  2b5edfbc
- J
  
  refine unittest test=develop · 4c9884e7
  由 jerrywgz 提交于 10月 17, 2018
  
  4c9884e7
- Q
  
  change elementwise_add to elementwise_add_to test=develop · 02259575
  由 Qiao Longfei 提交于 10月 17, 2018
  
  02259575
- Q
  
  sum_op support inplace · bd2b6d7f
  由 Qiao Longfei 提交于 10月 17, 2018
  
  bd2b6d7f
16 10月, 2018 2 次提交
- T
  fill constant add infervarshape, lookuptable clone lr var (#13830) · fa2ab334
  由 tangwei12 提交于 10月 16, 2018
```
* fill constant add infervarshape, lookuptable clone lr var

* test=develop

* add lookuptable ut, test=develop

* bug fix in transpliler about async with lookup table

* test=develop
```
  fa2ab334
- J
  
  roi_align for gpu · 8c79071d
  由 jerrywgz 提交于 10月 16, 2018
  
  8c79071d

PaddlePaddle / PaddleDetection 大约 1 年 前同步成功

PaddlePaddle / PaddleDetection
大约 1 年前同步成功