提交 · 17fa2ebd16257c0ddd120c5eae876d35f171c2dd · PaddlePaddle / Paddle-Lite

15 5月, 2019 1 次提交

remove dafault opencl kernel path (#1622) · 17fa2ebd

由 Jiaying Zhao 提交于 5月 15, 2019

* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure

* change funtion name

* change funtion name

* fix load_when_predict mode in opencl

* remove dafault opencl kernel path

17fa2ebd

13 5月, 2019 3 次提交

fix load_when_predict mode in opencl (#1619) · 4f7e31d9

由 Jiaying Zhao 提交于 5月 13, 2019

* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure

* change funtion name

* change funtion name

* fix load_when_predict mode in opencl

4f7e31d9

update feed fetch and softmax kernel in FPGA v2 track fixed#1615 (#1616) · b942f2de

由 qnqinan 提交于 5月 13, 2019

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update

* update feed and fetch kernel in FPGA v2 track

* update io file

* update feed fetch and softmax kernel in FPGA v2 track

b942f2de

S
Update ocr test case (#1605) · ca1119bf
由 Shuai Yuan 提交于 5月 13, 2019
```
* Update ocr test case

* format code

* format code
```
ca1119bf

10 5月, 2019 4 次提交
- Y
  
  remove thread unsafe dictionary (#1617) · bdf037cf
  由 Yanzhan Yang 提交于 5月 10, 2019
  
  bdf037cf
- Y
  
  change pixelFormat only when useAggressiveOptimization is set (#1614) · c3c6cbd3
  由 Yanzhan Yang 提交于 5月 10, 2019
  
  c3c6cbd3
- S
  
  Add comment for ARM Linux doc (#1604) · 0ee40193
  由 Shuai Yuan 提交于 5月 10, 2019
  
  0ee40193
- J
  io+softmax update for FPGA V1 track (#1613) · a422bfe2
  由 jameswu2014 提交于 5月 10, 2019
```
* V2-conv-hellocase pass & V1 verify-pass

* V1 paralvl equal to 2

* softmax channel =2 bug

* softmaxbug update2

* io update2
```
  a422bfe2
09 5月, 2019 2 次提交
- Y
  
  add useAggresiveOptimization param to control newly added optimization code branch (#1612) · cb945ceb
  由 Yanzhan Yang 提交于 5月 09, 2019
  
  cb945ceb
- J
  support V1 para equal to 2 (#1609) · 048a8ebe
  由 jameswu2014 提交于 5月 09, 2019
```
* V2-conv-hellocase pass & V1 verify-pass

* V1 paralvl equal to 2
```
  048a8ebe
08 5月, 2019 3 次提交

J

V2-conv-hellocase pass & V1 verify-pass (#1608) · a1cc931d
由 jameswu2014 提交于 5月 08, 2019

a1cc931d
Y
shift filter conversion process to loading phase (#1606) · 64aa8f05
由 Yanzhan Yang 提交于 5月 08, 2019
```
* shift filter conversion process to loading phase

* fix winograd edge case
```
64aa8f05

update io file to surport int8 tensor feed and fetch fixed#1602 (#1603) · b9ce0794

由 qnqinan 提交于 5月 08, 2019

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update

* update feed and fetch kernel in FPGA v2 track

* update io file

b9ce0794

07 5月, 2019 3 次提交

update feed and fetch kernel in FPGA v2 track fixed#1600 (#1601) · ae204098

由 qnqinan 提交于 5月 07, 2019

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update

* update feed and fetch kernel in FPGA v2 track

ae204098

S
Add readme for image preprocess and fix bug (#1597) · c576d9d4
由 Shuai Yuan 提交于 5月 07, 2019
```
* add comments for imagetools

* format code
```
c576d9d4

change funtion name (#1598) · 0aeb7490

由 Jiaying Zhao 提交于 5月 07, 2019

* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure

* change funtion name

* change funtion name

0aeb7490

06 5月, 2019 2 次提交
- Y
  implement winograd for metal depthwise 3x3 naively (#1596) · b4191a0b
  由 Yanzhan Yang 提交于 5月 06, 2019
```
* implement winograd for metal depthwise 3x3 naively

* keep half4 in non-winograd depthwise 3x3 to ensure precision
```
  b4191a0b
- J
  optimize GPU conv performance and structure (#1595) · b35e06f4
  由 Jiaying Zhao 提交于 5月 06, 2019
```
* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure
```
  b35e06f4
30 4月, 2019 4 次提交
- Y
  
  enable all mps conv layer (#1592) · 9315073f
  由 Yanzhan Yang 提交于 4月 30, 2019
  
  9315073f
- N
  
  fix semaphore crash (#1591) · be3cdaaf
  由 NazgulLee 提交于 4月 30, 2019
  
  be3cdaaf
- update kernel and related files for static quantization in FPGA v2 track fixed#1589 (#1590) · 491737d0
  由 qnqinan 提交于 4月 30, 2019
```
* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update
```
  491737d0
- S
  Update Build docs for ARM Linux CPU and GPU(OpenCL) (#1583) · 343ca535
  由 Shuai Yuan 提交于 4月 30, 2019
```
* format CMakeLists

* BugFix: lacking of header file of memset, strlen, stable_sort, n_copy

* Update ARM Linux CPU, GPU build docs for rk3399
```
  343ca535
29 4月, 2019 3 次提交
- Y
  fuse Conv-Add-Relu into one op (#1588) · abaf2fd3
  由 Yanzhan Yang 提交于 4月 29, 2019
```
* fuse Conv-Add-Relu into one op.

* Revert "fuse Conv-Add-Relu into one op."

This reverts commit 200be579.

* fuse Conv-Add-Relu into one op
```
  abaf2fd3
- W
  
  initTexture interface modeify to throw an exception (#1587) · a03c130a
  由 WayneLiu 提交于 4月 29, 2019
  
  a03c130a
- update kernel and related files for static quantization in FPGA v2 track fixed#1584 (#1585) · 6dc40742
  由 qnqinan 提交于 4月 29, 2019
```
* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update
```
  6dc40742
28 4月, 2019 1 次提交
- H
  Fix memory leak if tensor was created outside of global scope, and fix gemv bugs (#1581) · b734c439
  由 Houjiang Chen 提交于 4月 28, 2019
```
* Fix memory leak if tensor was created outside of global scope

* Fix gemv bugs
```
  b734c439
26 4月, 2019 3 次提交
- Y
  Merge pull request #1582 from yangyanzhan/develop · 980b855d
  由 Yanzhan Yang 提交于 4月 26, 2019
```
fix MPSCNN ConvAdd implementation.
```
  980b855d
- Y
  
  fix MPSCNN ConvAdd implementation. · f3d4f1b8
  由 yangyanzhan 提交于 4月 26, 2019
  
  f3d4f1b8
- J
  Merge pull request #1579 from smilejames/develop · c2f69ebd
  由 Jiaying Zhao 提交于 4月 26, 2019
```
adjust gpu code structure
```
  c2f69ebd
25 4月, 2019 8 次提交
- Z
  
  gpu conv_bn_add_relu use 1x1 optimise kernel · b822fa08
  由 zhaojiaying01 提交于 4月 25, 2019
  
  b822fa08
- Z
  
  Merge remote-tracking branch 'origin/develop' into develop · e026faad
  由 zhaojiaying01 提交于 4月 25, 2019
  
  e026faad
- Z
  
  format code style · 8758c017
  由 zhaojiaying01 提交于 4月 25, 2019
  
  8758c017
- J
  
  Merge branch 'develop' into develop · 1ff4bc93
  由 Jiaying Zhao 提交于 4月 25, 2019
  
  1ff4bc93
- Z
  
  adjust gpu code structure · 014fb131
  由 zhaojiaying01 提交于 4月 25, 2019
  
  014fb131
- J
  Merge pull request #1577 from smilejames/develop · 29680f39
  由 Jiaying Zhao 提交于 4月 25, 2019
```
fix gpu conv_kernel
```
  29680f39
- Z
  
  format code style · 99131efa
  由 zhaojiaying01 提交于 4月 25, 2019
  
  99131efa
- Z
  
  fix gpu conv_kernel · 31130d35
  由 zhaojiaying01 提交于 4月 25, 2019
  
  31130d35
24 4月, 2019 1 次提交

Give advice for Alloc function users (#1575) · 62f4ab13

由 Shuai Yuan 提交于 4月 24, 2019

* BugFix: add input parameters checking for Alloc

* Give advice for Alloc function users

* Give advice for Alloc function users

62f4ab13

23 4月, 2019 2 次提交
- T
  
  update ndk url (#1562) · 7fc088b4
  由 tensor-tang 提交于 4月 23, 2019
  
  7fc088b4
- H
  
  Fix compilation on Raspberry PI3, and fix some code style (#1566) · df028ce2
  由 Houjiang Chen 提交于 4月 23, 2019
  
  df028ce2