提交 · fc659486f008a345ced3b0fc3712f0193df812fc · PaddlePaddle / Paddle-Lite

08 1月, 2020 1 次提交
- T
  
  fix fpga quant_dequant_op_fuser bug · 38ff42f9
  由 tienfeek 提交于 1月 08, 2020
  
  38ff42f9
27 12月, 2019 1 次提交
- C
  
  merged from 1.4.0 · 64a0feac
  由 chonwhite 提交于 12月 27, 2019
  
  64a0feac
26 12月, 2019 1 次提交
- M
  
  fix:delete useless code · 32177924
  由 MyPandaShaoxiang 提交于 12月 26, 2019
  
  32177924
25 12月, 2019 1 次提交
- C
  
  attention works · 9c15846a
  由 chonwhite 提交于 12月 25, 2019
  
  9c15846a
23 12月, 2019 4 次提交
- C
  
  attention works · f010edd0
  由 chonwhite 提交于 12月 23, 2019
  
  f010edd0
- C
  
  added one_hot operator · b4e07620
  由 chonwhite 提交于 12月 23, 2019
  
  b4e07620
- W
  add sequence_pool_concat fuse and kernel test=develop (#2645) · 04ab34b6
  由 Wilber 提交于 12月 23, 2019
```
add sequence_pool_concat fuse pass

add fuse kernel
```
  04ab34b6
- Y
  
  [ARM] add grid_sampler op and ut, test=develop (#2598) · 9875843e
  由 yiicy 提交于 12月 23, 2019
  
  9875843e
21 12月, 2019 1 次提交
- Z
  [XPU] add layer_norm bridge and unit test (#2640) · aadb65d2
  由 zhupengyang 提交于 12月 21, 2019
```
test=develop
```
  aadb65d2
20 12月, 2019 3 次提交
- Z
  [XPU] add reshape bridge and unit test (#2621) · 7bd142bd
  由 zhupengyang 提交于 12月 20, 2019
```
test=develop
```
  7bd142bd
- W
  add var_conv_2d_relu pass test=develop (#2631) · 810eb089
  由 Wilber 提交于 12月 20, 2019
```
add var_conv_2d + relu fuse pass
```
  810eb089
- Z
  [XPU] add transpose bridge and unit test (#2630) · 3ef94cd4
  由 zhupengyang 提交于 12月 20, 2019
```
* [XPU] add transpose bridge and unit test

test=develop
```
  3ef94cd4
19 12月, 2019 3 次提交
- W
  optimize cuda kernel test=develop (#2628) · 62044067
  由 Wilber 提交于 12月 19, 2019
```
* optimize content-dnn cuda kernel
```
  62044067
- X
  feature: update fpga kernel patch (#2627) · 6b175596
  由 xiaogang 提交于 12月 19, 2019
```
* feature: update fpga kernel patch
```
  6b175596
- Y
  [ARM] change global pooling choose kernel policy, test=develop (#2602) · 187bf7c5
  由 yiicy 提交于 12月 19, 2019
```
* [ARM] change global pooling choose kernel policy, test=develop
```
  187bf7c5
18 12月, 2019 4 次提交
- M
  style: style fix · 1a9928a9
  由 MyPandaShaoxiang 提交于 12月 18, 2019
```
test=develop
```
  1a9928a9
- M
  feature: update fpga kernel patch · 1893489c
  由 MyPandaShaoxiang 提交于 12月 18, 2019
```
test=develop
```
  1893489c
- C
  
  shared library works · b02b1822
  由 chonwhite 提交于 12月 18, 2019
  
  b02b1822
- J
  Support Mask RCNN2 (#2588) · a39f92ea
  由 juncaipeng 提交于 12月 18, 2019
```
* Support Mask RCNN2 (#2588)
```
  a39f92ea
17 12月, 2019 3 次提交
- H
  
  [lite][arm] add conv+relu6/leakyRelu fusion (#2599) · 0314aa1e
  由 HappyAngel 提交于 12月 17, 2019
  
  0314aa1e
- X
  Develop lite reshape (#2613) · 3368a1e0
  由 xiebaiyuan 提交于 12月 17, 2019
```
* add reshape opencl kernel && optimise conv 1x1 ,test=develop

* add reshape opencl kernel && optimise conv 1x1 &&code style ,test=develop

* add reshape opencl kernel && optimise conv 1x1 &&code style ,test=develop
```
  3368a1e0
- Y
  
  add fp16 opencl kernel. fix nhwc as imagedefault for opencl layout. test=develop (#2616) · cec596d5
  由 Yuan Shuai 提交于 12月 17, 2019
  
  cec596d5
16 12月, 2019 3 次提交

[LITE][OPENCL] Add relu image2d kernel unit test, Fix conv2d_1x1, relu, layout... · cc46d43c

由 Yuan Shuai 提交于 12月 16, 2019

[LITE][OPENCL] Add relu image2d kernel unit test, Fix conv2d_1x1, relu, layout using new Image2D Layout (#2564)

* add 3 layout for opencl image. test=develop

* add relu image2d test. test=develop

cc46d43c

[LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel (#2601) · cff0c364

由 Jiaying Zhao 提交于 12月 16, 2019

* [LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel

* [LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel. test=develop

* [LITE][OPENCL] Add Pool opencl kernel. test=develop

cff0c364

C

mobilenet works · e9833139
由 chonwhite 提交于 12月 16, 2019

e9833139

15 12月, 2019 1 次提交
- W
  optimize search_grnn test=develop (#2608) · b65a6dc9
  由 Wilber 提交于 12月 15, 2019
```
optimize search_grnn
```
  b65a6dc9
13 12月, 2019 3 次提交
- C
  
  code format · b65c1191
  由 chonwhite 提交于 12月 13, 2019
  
  b65c1191
- C
  
  format code · 51d144f3
  由 chonwhite 提交于 12月 13, 2019
  
  51d144f3
- H
  [LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at... · 1dbcd51d
  由 hong19860320 提交于 12月 13, 2019
```
[LITE][NPU][XPU] Refine subgraph pass, and support NPU/XPU model generation at execution time (#2576)
```
  1dbcd51d
12 12月, 2019 1 次提交

[LITE][OPENCL] Add conv2d_1x1 opencl kernel (#2591) · 06e754c9

由 xiebaiyuan 提交于 12月 12, 2019

* add opencl conv1x1 image impl and unit test pass with relu & bias,
add layout_compute --> buffer2image float32 --> with unit test pass
suite checked test for more situation , test=develop

* add opencl conv1x1 image impl and unit test pass with relu & bias,
add layout_compute --> buffer2image float32 --> with unit test pass
suite checked test for more situation , test=develop

* fix white space cpp lint , test=develop

06e754c9

11 12月, 2019 2 次提交
- T
  
  add winograd f23 implement (#2584) · 7f7be7db
  由 TianXiaogang 提交于 12月 11, 2019
  
  7f7be7db
- C
  
  VGG-SSD works · 4dddc907
  由 chonwhite 提交于 12月 11, 2019
  
  4dddc907
10 12月, 2019 3 次提交
- H
  
  modify code_style of CMakeList.txt to make ci_build_test_server able to work on gcc_4.8.2 · e6582cb6
  由 huzhiqiang 提交于 12月 10, 2019
  
  e6582cb6
- Y
  
  [ARM] add instance norm op and ut, test=develop (#2578) · 933a3724
  由 yiicy 提交于 12月 10, 2019
  
  933a3724
- Z
  [NPU] add argamx op bridge and unit test (#2580) · 5963b4ba
  由 zhupengyang 提交于 12月 10, 2019
```
test=develop
```
  5963b4ba
09 12月, 2019 2 次提交
- C
  
  removed some comments · 945aa36f
  由 chonwhite 提交于 12月 09, 2019
  
  945aa36f
- Z
  [NPU] support relu6 (#2582) · 68b65a76
  由 zhupengyang 提交于 12月 09, 2019
```
test=develop
```
  68b65a76
08 12月, 2019 1 次提交
- L
  
  Add fc op on lite x86 platform (#2568) · 49f67ba7
  由 liu zhengxi 提交于 12月 08, 2019
  
  49f67ba7
07 12月, 2019 2 次提交

Z
[NPU] add unsqueeze op bridge and unit test (#2570) · 833aa8a7
由 zhupengyang 提交于 12月 07, 2019
```
test=develop
```
833aa8a7

Support mask_rcnn (#2484) · cf31b835

由 juncaipeng 提交于 12月 07, 2019

* add arm split lod tensor, test=develop

* add arm merge lod tensor, test=develop

* update split merge lod tensor, test=develop

* add reduce_prob op, test=develop

* support mask_rcnn succeed, test=develop

cf31b835