提交 · 2b32484a4f87dee95a17fe81b19417a6587a3a8c · PaddlePaddle / Paddle-Lite

21 5月, 2020 1 次提交
- C
  
  mereged with upstream/develope · e5f6ce88
  由 chonwhite 提交于 5月 21, 2020
  
  e5f6ce88
17 3月, 2020 2 次提交

feature: buffer sharing, test=develop (#3161) · de74ee37

由石晓伟提交于 3月 17, 2020

* feature: buffer sharing, test=develop

* fix the warning of buffer.h, test=develop

* test cuda only if necessary, test=develop

de74ee37

石

feature: buffer sharing, test=develop (#3161) · e04399ba

由石晓伟提交于 3月 17, 2020

* feature: buffer sharing, test=develop

* fix the warning of buffer.h, test=develop

* test cuda only if necessary, test=develop

e04399ba

24 2月, 2020 2 次提交

[LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all... · 55b45651

由 Yuan Shuai 提交于 2月 24, 2020

[LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all OpenCL image kernel. test=develop (#2964)

* [LITE][OPENCL] support fp16 for cl_image_converter, layout, activation image kernel. test=develop

* add conv, depthwise and UT. test=develop

* add pool, conv, nearest_interp kernel. test=develop

* support fp16 for scale, reshape, concat, fc buffer opencl kernel. test=develop

* refactor for mul opencl buffer kernel. test=develop

* support fp16 for elementwise_mul opecl image kernel. test=develop

* support fp16 for elementwise_mul opencl image kernel. test=develop

* support fp16 for ele_add, fuse_ele_add_act opencl kernel. test=develop

* rename io_copy. test=develop

* mobilenetv1,v2 passed on 855. test=develop

* fix opt for opencl. test=develop

55b45651

[LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all... · 8b90a0c7

由 Yuan Shuai 提交于 2月 24, 2020

[LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all OpenCL image kernel. test=develop (#2964)

* [LITE][OPENCL] support fp16 for cl_image_converter, layout, activation image kernel. test=develop

* add conv, depthwise and UT. test=develop

* add pool, conv, nearest_interp kernel. test=develop

* support fp16 for scale, reshape, concat, fc buffer opencl kernel. test=develop

* refactor for mul opencl buffer kernel. test=develop

* support fp16 for elementwise_mul opecl image kernel. test=develop

* support fp16 for elementwise_mul opencl image kernel. test=develop

* support fp16 for ele_add, fuse_ele_add_act opencl kernel. test=develop

* rename io_copy. test=develop

* mobilenetv1,v2 passed on 855. test=develop

* fix opt for opencl. test=develop

8b90a0c7

14 2月, 2020 1 次提交
- T
  FPGA support quantitative model · ffb7ead1
  由 tienfeek 提交于 2月 14, 2020
```
test=develop
```
  ffb7ead1
11 2月, 2020 2 次提交

Optimize the InferShape of several operators. (#2839) · 87e30f5c

由 Yiqun Liu 提交于 2月 11, 2020

* Optimize the InferShape of several operators.
test=develop

* Remove the new function, resize and CheckPositive in DDim.
test=develop

* Fix a bug in fc_op's InferShape.
test=develop

87e30f5c

Optimize the InferShape of several operators. (#2839) · 800f5ce6

由 Yiqun Liu 提交于 2月 11, 2020

* Optimize the InferShape of several operators.
test=develop

* Remove the new function, resize and CheckPositive in DDim.
test=develop

* Fix a bug in fc_op's InferShape.
test=develop

800f5ce6

08 2月, 2020 2 次提交
- Y
  Implement a class PrecisionTypeTrait to get the PrecisionType of a c++ data type. (#2835) · ea9e150d
  由 Yiqun Liu 提交于 2月 08, 2020
```
test=develop
```
  ea9e150d
- Y
  Implement a class PrecisionTypeTrait to get the PrecisionType of a c++ data type. (#2835) · e73d4652
  由 Yiqun Liu 提交于 2月 08, 2020
```
test=develop
```
  e73d4652
08 1月, 2020 2 次提交

[LITE][CORE][NPU][XPU] Recording the data type when mutable_data() is called,... · 7a3ea278

由 hong19860320 提交于 1月 08, 2020

[LITE][CORE][NPU][XPU] Recording the data type when mutable_data() is called, and supporting the type inference from the tensor for the op bridges (#2735)

7a3ea278

[LITE][CORE][NPU][XPU] Recording the data type when mutable_data() is called,... · 6e4acdcd

由 hong19860320 提交于 1月 08, 2020

[LITE][CORE][NPU][XPU] Recording the data type when mutable_data() is called, and supporting the type inference from the tensor for the op bridges (#2735)

6e4acdcd

25 12月, 2019 2 次提交
- J
  fix mask rcnn error when run twice, test=develop (#2675) · 1ea51762
  由 juncaipeng 提交于 12月 25, 2019
```
add clear for tensor
```
  1ea51762
- J
  fix mask rcnn error when run twice, test=develop (#2675) · cd49b0a3
  由 juncaipeng 提交于 12月 25, 2019
```
add clear for tensor
```
  cd49b0a3
17 12月, 2019 2 次提交
- 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
- Y
  
  add fp16 opencl kernel. fix nhwc as imagedefault for opencl layout. test=develop (#2616) · 24c98e60
  由 Yuan Shuai 提交于 12月 17, 2019
  
  24c98e60
16 12月, 2019 2 次提交

[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

[LITE][OPENCL] Add depthwise_conv_3x3 opencl kernel (#2601) · 600c8c20

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

600c8c20

15 10月, 2019 2 次提交

[LITE][OPENCL] Fix layout, target pass for OpenCL, add macro of... · 26d05370

由 Yuan Shuai 提交于 10月 15, 2019

[LITE][OPENCL] Fix layout, target pass for OpenCL, add macro of CONVERT_TYPE_TO and READ/WRITE image, memory reuse in ResetLazyImage2D (#2170)

* add macro of CONVERT_TYPE_TO and READ/WRITE image. test=develop

* add data type control. test=develop

* fix io op as general layout and precision. test=develop

* Fix memory reuse strategy for opencl image2d. test=develop

* remove std::array, std::map in about opencl backend. test=develop

26d05370

[LITE][OPENCL] Fix layout, target pass for OpenCL, add macro of... · 72c11758

由 Yuan Shuai 提交于 10月 15, 2019

[LITE][OPENCL] Fix layout, target pass for OpenCL, add macro of CONVERT_TYPE_TO and READ/WRITE image, memory reuse in ResetLazyImage2D (#2170)

* add macro of CONVERT_TYPE_TO and READ/WRITE image. test=develop

* add data type control. test=develop

* fix io op as general layout and precision. test=develop

* Fix memory reuse strategy for opencl image2d. test=develop

* remove std::array, std::map in about opencl backend. test=develop

72c11758

11 10月, 2019 2 次提交

[LITE][OPENCL] support image2d type (#2158) · 74074146

由 Yuan Shuai 提交于 10月 11, 2019

* [LITE][OPENCL] support image2d. test=develop

* add context changed with consider image*. test=develop

* add layout, relu image kernels. test=develop

* replace image_data with data, mutable_image_data with mutable_data, test=develop

* comment unused var. test=develop

* remove unused var. test=develop

74074146

[LITE][OPENCL] support image2d type (#2158) · 77cdbdce

由 Yuan Shuai 提交于 10月 11, 2019

* [LITE][OPENCL] support image2d. test=develop

* add context changed with consider image*. test=develop

* add layout, relu image kernels. test=develop

* replace image_data with data, mutable_image_data with mutable_data, test=develop

* comment unused var. test=develop

* remove unused var. test=develop

77cdbdce

07 9月, 2019 2 次提交

add lite x86 ops for ASR test=develop (#1981) · 25b775d6

由 lijianshe02 提交于 9月 07, 2019

* add lite x86 ops for ASR test=develop

* add lite x86 ops for ASR test=develop

* fix x86 ci run test problems test=develop

* fix mkl path for CI test=develop

25b775d6

add lite x86 ops for ASR test=develop (#1981) · 7014a76b

由 lijianshe02 提交于 9月 07, 2019

* add lite x86 ops for ASR test=develop

* add lite x86 ops for ASR test=develop

* fix x86 ci run test problems test=develop

* fix mkl path for CI test=develop

7014a76b

03 9月, 2019 2 次提交
- H
  
  create backends directory and move hardware backends into it (#1954) · fede4a1c
  由 huzhiqiang 提交于 9月 03, 2019
  
  fede4a1c
- H
  
  create backends directory and move hardware backends into it (#1954) · 31ee212a
  由 huzhiqiang 提交于 9月 03, 2019
  
  31ee212a
02 9月, 2019 2 次提交

Add ops and fix bugs for Faster RCNN (#1942) · cfd5abe5

由 juncaipeng 提交于 9月 02, 2019

* add ops for faster rcnn

* disable test for generate_proposals and roi_align, test=develop

* remove .swp file

* remove log in tensor slice

* finish the unit test for roi_align, test=develop

* add box_clip op and fix tensor slice bug

* remove add four op twice

* rewrite the implement for box_coder and sequence_expand, add faster_rcnn_test, test=develop

* fix test bug of box_clip in x86 server, test=develop

cfd5abe5

Add ops and fix bugs for Faster RCNN (#1942) · 635b4958

由 juncaipeng 提交于 9月 02, 2019

* add ops for faster rcnn

* disable test for generate_proposals and roi_align, test=develop

* remove .swp file

* remove log in tensor slice

* finish the unit test for roi_align, test=develop

* add box_clip op and fix tensor slice bug

* remove add four op twice

* rewrite the implement for box_coder and sequence_expand, add faster_rcnn_test, test=develop

* fix test bug of box_clip in x86 server, test=develop

635b4958

30 8月, 2019 2 次提交

add precision and persistable attrs for the tensor. (#1899) · 79bdecdd

由 Zhen Wang 提交于 8月 30, 2019

* Add precision and persistable attrs for the tensor. And fix cxx light and full api demo.

* update precision2string methods. test=develop

* move the save logic to the front of the run in mobilenetv1_full_api.cc, test=develop.

* add comments for UpdateVarsOfProgram. test=develop

79bdecdd

add precision and persistable attrs for the tensor. (#1899) · e2e07fa4

由 Zhen Wang 提交于 8月 30, 2019

* Add precision and persistable attrs for the tensor. And fix cxx light and full api demo.

* update precision2string methods. test=develop

* move the save logic to the front of the run in mobilenetv1_full_api.cc, test=develop.

* add comments for UpdateVarsOfProgram. test=develop

e2e07fa4

29 8月, 2019 2 次提交

ad ops for faster rcnn, including affine_channel, anchor_generator,... · f3035827

由 juncaipeng 提交于 8月 29, 2019

ad ops for faster rcnn, including affine_channel, anchor_generator, generate_proposals and roi_align (#1895)

* add ops for faster rcnn

* disable test for generate_proposals and roi_align, test=develop

* remove .swp file

* remove log in tensor slice

* finish the unit test for roi_align, test=develop

f3035827

ad ops for faster rcnn, including affine_channel, anchor_generator,... · 53b05ce8

由 juncaipeng 提交于 8月 29, 2019

ad ops for faster rcnn, including affine_channel, anchor_generator, generate_proposals and roi_align (#1895)

* add ops for faster rcnn

* disable test for generate_proposals and roi_align, test=develop

* remove .swp file

* remove log in tensor slice

* finish the unit test for roi_align, test=develop

53b05ce8

16 8月, 2019 2 次提交
- Y
  
  publish lite (#1800) · 7a9e16c0
  由 Yan Chunwei 提交于 8月 16, 2019
  
  7a9e16c0
- Y
  
  publish lite (#1800) · 699d6cd0
  由 Yan Chunwei 提交于 8月 16, 2019
  
  699d6cd0