提交 · 176f90c44b4685dcb105806bfc85b1adae68fd54 · PaddlePaddle / Paddle-Lite

23 10月, 2019 1 次提交
- X
  
  fix out range in conv 1x1 for nano yolo ,test=develop (#2246) · 176f90c4
  由 xiebaiyuan 提交于 10月 23, 2019
  
  176f90c4
21 10月, 2019 1 次提交
- J
  
  add GetExceptionMsg for paddle_inference_api. test=develop (#2231) · f623b1d4
  由 Jiaying Zhao 提交于 10月 21, 2019
  
  f623b1d4
17 10月, 2019 1 次提交
- S
  
  fix “CL_INVALID_KERNEL_ARGS ” error， test=develop (#2213) · 0baf7c05
  由 StarryRain 提交于 10月 17, 2019
  
  0baf7c05
16 10月, 2019 2 次提交
- J
  
  Open merge_cl_to_so switch and delete -I(cl_path) build option. test=develop (#2206) · eb7c5829
  由 Jiaying Zhao 提交于 10月 16, 2019
  
  eb7c5829
- X
  
  support global pooling ... test=develop (#2204) · 9f867daf
  由 xiebaiyuan 提交于 10月 16, 2019
  
  9f867daf
12 10月, 2019 1 次提交
- J
  
  fix clang compile error. test=develop (#2180) · 9aa795ca
  由 Jiaying Zhao 提交于 10月 12, 2019
  
  9aa795ca
11 10月, 2019 1 次提交
- Y
  
  1. fix group logic for convolution op. 2. add pixel shuffle op for OpenCL. (#2178) · e0aafc03
  由 Yanzhan Yang 提交于 10月 11, 2019
  
  e0aafc03
10 10月, 2019 2 次提交
- Y
  1. improve n-fold quantification algorithm by introducing a minimal size for... · 148ef22a
  由 Yanzhan Yang 提交于 10月 10, 2019
```
1. improve n-fold quantification algorithm by introducing a minimal size for each fold. 2. automatically search for best n for n-fold algorithm. (#2167)
```
  148ef22a
- X
  
  fix an calc bug in test-mobilenetgpu (#2162) · 5245133a
  由 xiebaiyuan 提交于 10月 10, 2019
  
  5245133a
09 10月, 2019 4 次提交
- Y
  add n-fold quantification algorithm (#2164) · 1a84af53
  由 Yanzhan Yang 提交于 10月 09, 2019
```
* 1. add quantification_fold parameter. 2. support quantification test in run.py.

* implement n-fold quantification
```
  1a84af53
- X
  open cl mem optimise, split with cpu codes. fix a bug when some memory is not equal 4 . (#2161) · 499fa1b8
  由 xiebaiyuan 提交于 10月 09, 2019
```
* open cl mem optimise, split with cpu codes.
fix a bug when some memory is not equal 4 .

* open cl mem optimise, split with cpu codes.   fix a bug when some memory is not equal 4  fix bad des
```
  499fa1b8
- Z
  
  fix crash in some platform (#2159) · 36d8b5bc
  由 zp7 提交于 10月 09, 2019
  
  36d8b5bc
- X
  
  paddle mobile runtime cl memory optimise. test=develop (#2160) · 5506defe
  由 xiebaiyuan 提交于 10月 09, 2019
  
  5506defe
08 10月, 2019 1 次提交
- J
  
  add pre and post process in feed and fetch kernel test=develop (#2157) · ebae97f4
  由 Jiaying Zhao 提交于 10月 08, 2019
  
  ebae97f4
27 9月, 2019 1 次提交
- N
  
  optimize instance norm. test=develop (#2120) · 7ff455ac
  由 NazgulLee 提交于 9月 27, 2019
  
  7ff455ac
26 9月, 2019 1 次提交
- Z
  
  fix crash (#2139) · 54ae37b6
  由 zp7 提交于 9月 26, 2019
  
  54ae37b6
25 9月, 2019 1 次提交

get opencl kernel_work_group_size (#2123) · f61a3549

由 StarryRain 提交于 9月 25, 2019

* get opencl kernel_work_group_size and set local_work_group_size for conv and conv_trans kernel of GAN, test=develop

* fix fpga CI error, test=develop

* fix fpga CI error, test=develop

* auto set local work group size according to devices

* Optimal OPENCL conv_trans_7x7 Performance , test=develop

* fix CI error, test=develop

f61a3549

17 9月, 2019 2 次提交
- Y
  fix new_scale & new_bias crash test=develop (#2055) · bf024198
  由 Yanzhan Yang 提交于 9月 17, 2019
```
* fix new_scale & new_bias crash test=develop

* fix new_bias & new_scale in GPU test=develop
```
  bf024198
- Y
  
  add assign_value op for gpu test=develop (#2053) · a75030e0
  由 Yanzhan Yang 提交于 9月 17, 2019
  
  a75030e0
16 9月, 2019 1 次提交
- Y
  
  refine paddle_inference_api.h test=develop (#2048) · b386cde2
  由 Yanzhan Yang 提交于 9月 16, 2019
  
  b386cde2
12 9月, 2019 3 次提交
- S
  add opencl conv_trans_op (#2031) · 3d45af54
  由 StarryRain 提交于 9月 12, 2019
```
* add opencl  depthwise_conv_trans_op

* test=develop

* Optimal OPENCL conv_3x3S2 Performance

* test=develop

* Optimal OPENCL conv_trans_3x3s2 Performance , test=develop

* add opencl conv_trans_op, test=develop
```
  3d45af54
- N
  
  optimize conv7*7, compute 2 point in 1 thread. test=develop (#2028) · d4efca3a
  由 NazgulLee 提交于 9月 12, 2019
  
  d4efca3a
- Z
  
  fix gpu load memory leak,test=develop (#2027) · c45339ce
  由 zp7 提交于 9月 12, 2019
  
  c45339ce
11 9月, 2019 1 次提交

Optimal OPENCL conv_trans_3x3s2 Performance (#2015) · a776ffb7

由 StarryRain 提交于 9月 11, 2019

* add opencl  depthwise_conv_trans_op

* test=develop

* Optimal OPENCL conv_3x3S2 Performance

* test=develop

* Optimal OPENCL conv_trans_3x3s2 Performance , test=develop

a776ffb7

10 9月, 2019 2 次提交
- N
  
  optimize instancenorm local workgroup computation. test=develop (#2001) · 5f19524c
  由 NazgulLee 提交于 9月 10, 2019
  
  5f19524c
- S
  Optimal OPENCL conv_3x3 Performance (#1994) · 5d9b0471
  由 StarryRain 提交于 9月 10, 2019
```
* add opencl  depthwise_conv_trans_op

* test=develop

* Optimal OPENCL conv_3x3S2 Performance

* test=develop
```
  5d9b0471
09 9月, 2019 2 次提交
- Y
  fix vector out of range crash test=develop (#1999) · f38a741a
  由 Yanzhan Yang 提交于 9月 09, 2019
```
* fix vector out of range crash test=develop

* fix style test=develop
```
  f38a741a
- N
  
  fusion instancenorm and relu. test=develop (#1986) · 3ea21620
  由 NazgulLee 提交于 9月 09, 2019
  
  3ea21620
06 9月, 2019 1 次提交
- Y
  fix ios CPU preprocess test=develop (#1972) · 22bcb8ba
  由 Yanzhan Yang 提交于 9月 06, 2019
```
* fix ios CPU preprocess test=develop

* fix style test=develop
```
  22bcb8ba
03 9月, 2019 6 次提交
- Z
  
  add op init profile (#1962) · 3618f488
  由 zp7 提交于 9月 03, 2019
  
  3618f488
- Y
  accelerate opencl compilation time test=develop (#1961) · 7b7e0d90
  由 Yanzhan Yang 提交于 9月 03, 2019
```
* accelerate opencl compilation time test=develop

* fix style test=develop
```
  7b7e0d90
- Y
  
  add cl status check test=develop (#1956) · 088d741f
  由 Yanzhan Yang 提交于 9月 03, 2019
  
  088d741f
- Y
  fix variant memory leak (#1951) · 833c405d
  由 Yanzhan Yang 提交于 9月 03, 2019
```
* fix variant memory leak test=develop

* fix variant memory leak & fix style test=develop

* fix cpplint test=develop
```
  833c405d
- H
  fix getgputime (#1950) · 4f332056
  由 Huie 提交于 9月 03, 2019
```
* 1.add density_prior_box for gpu.
2.add flatten2 for gpu.
3.add concat 4 inputs size for gpu.
4.fix pool.
5.fix transpose2
test=develop

* 1.fix GetGPUTime
test=develop
```
  4f332056
- S
  add opencl depthwise_conv_trans_op (#1949) · eb6d84d1
  由 StarryRain 提交于 9月 03, 2019
```
* add opencl  depthwise_conv_trans_op

* test=develop
```
  eb6d84d1
01 9月, 2019 1 次提交
- N
  
  opencl support pad2d, instancenorm, convtranspose and tanh. test=develop (#1940) · c2f90b59
  由 NazgulLee 提交于 9月 01, 2019
  
  c2f90b59
29 8月, 2019 1 次提交

refine toolchain test=develop (#1904) · b120bccb

由 Yanzhan Yang 提交于 8月 29, 2019

* refine toolchain test=develop

* fix wrap compilation error

* fix yolov3 armv8 compilation test=develop

* revert to armv7 as default test=develop

* fix fpga compilation test=develop

b120bccb

28 8月, 2019 3 次提交
- Y
  
  fix yolov3 concat op test=develop (#1901) · 0af82ab3
  由 Yanzhan Yang 提交于 8月 28, 2019
  
  0af82ab3
- Y
  
  fix elementwise_add && fix run.py && add namespace change script (#1898) · e520e49e
  由 Yanzhan Yang 提交于 8月 28, 2019
  
  e520e49e
- Y
  
  refine wrap to support GPU test=develop (#1892) · c0a0ea60
  由 Yanzhan Yang 提交于 8月 28, 2019
  
  c0a0ea60