提交 · 2b32484a4f87dee95a17fe81b19417a6587a3a8c · PaddlePaddle / Paddle-Lite

26 5月, 2020 1 次提交
- H
  
  merge conflicts · e5f779de
  由 hanbuhe 提交于 5月 26, 2020
  
  e5f779de
25 5月, 2020 2 次提交
- Y
  [LITE][PROFILE] Add ops calc. of operators for profiler. test=develop (#3680) · b6533389
  由 Yuan Shuai 提交于 5月 25, 2020
```
* add calltime/gops for summary. test=develop

* fix act case for kunk. test=develop
```
  b6533389
- Y
  [LITE][PROFILE] Add ops calc. of operators for profiler. test=develop (#3680) · 7878b3d2
  由 Yuan Shuai 提交于 5月 25, 2020
```
* add calltime/gops for summary. test=develop

* fix act case for kunk. test=develop
```
  7878b3d2
22 5月, 2020 5 次提交
- H
  
  [cherry-pick][BUG FIX] fix the issue that opt can not convert quantized model (#3683) · 6dcbe32b
  由 huzhiqiang 提交于 5月 22, 2020
  
  6dcbe32b
- H
  
  [cherry-pick][BUG FIX] fix the issue that opt can not convert quantized model (#3683) · f779a5b9
  由 huzhiqiang 提交于 5月 22, 2020
  
  f779a5b9
- C
  
  added fc_relu and fc_sigmoid fusion · fb345c46
  由 chonwhite 提交于 5月 22, 2020
  
  fb345c46
- C
  
  Skip fusing conv and elementwise when the bias of elementwise has two output, test=develop (#3679) · b97da301
  由 cc 提交于 5月 22, 2020
  
  b97da301
- C
  
  Skip fusing conv and elementwise when the bias of elementwise has two output, test=develop (#3679) · 070a2970
  由 cc 提交于 5月 22, 2020
  
  070a2970
21 5月, 2020 3 次提交
- C
  
  mereged with upstream/develope · e5f6ce88
  由 chonwhite 提交于 5月 21, 2020
  
  e5f6ce88
- Y
  [LITE][PROFILE] Enhance ARM CPU profiler with real backend kernel name (#3674) · d1328b25
  由 Yuan Shuai 提交于 5月 21, 2020
```
* [LITE][PROFILE] Enhance ARM CPU profiler with real backend kernel. test=develop
```
  d1328b25
- Y
  [LITE][PROFILE] Enhance ARM CPU profiler with real backend kernel name (#3674) · 049af076
  由 Yuan Shuai 提交于 5月 21, 2020
```
* [LITE][PROFILE] Enhance ARM CPU profiler with real backend kernel. test=develop
```
  049af076
20 5月, 2020 1 次提交
- C
  
  modified nms · 00aa83e5
  由 chonwhite 提交于 5月 20, 2020
  
  00aa83e5
18 5月, 2020 4 次提交
- Y
  [LITE][OPENCL] Enhance Profiler for OpenCL with in/out/filter shape,... · e18ba102
  由 Yuan Shuai 提交于 5月 18, 2020
```
[LITE][OPENCL] Enhance Profiler for OpenCL with in/out/filter shape, macs/macs_ps, real backend kernel etc. (#3641)

* [LITE][OPENCL] Enhance Precision Profiler for OpenCL. test=develop
```
  e18ba102
- Y
  [LITE][OPENCL] Enhance Profiler for OpenCL with in/out/filter shape,... · 53a6f3bc
  由 Yuan Shuai 提交于 5月 18, 2020
```
[LITE][OPENCL] Enhance Profiler for OpenCL with in/out/filter shape, macs/macs_ps, real backend kernel etc. (#3641)

* [LITE][OPENCL] Enhance Precision Profiler for OpenCL. test=develop
```
  53a6f3bc
- H
  
  [Framework][ModelType] Add Shape&Precision information into optimized model (#3643) · 05690463
  由 huzhiqiang 提交于 5月 18, 2020
  
  05690463
- H
  
  [Framework][ModelType] Add Shape&Precision information into optimized model (#3643) · 546d4da8
  由 huzhiqiang 提交于 5月 18, 2020
  
  546d4da8
17 5月, 2020 2 次提交
- H
  
  [Lib Symbol][Python lib] strip third_party symbol in python lib and mac lib (#3630) · df3be6f1
  由 huzhiqiang 提交于 5月 17, 2020
  
  df3be6f1
- H
  
  [Lib Symbol][Python lib] strip third_party symbol in python lib and mac lib (#3630) · a24d4dd1
  由 huzhiqiang 提交于 5月 17, 2020
  
  a24d4dd1
15 5月, 2020 2 次提交
- Z
  
  [NPU] refine subgraph name (#3624) · 51f83515
  由 zhupengyang 提交于 5月 15, 2020
  
  51f83515
- Z
  
  [NPU] refine subgraph name (#3624) · d49bd42c
  由 zhupengyang 提交于 5月 15, 2020
  
  d49bd42c
13 5月, 2020 4 次提交
- H
  
  [X86][Demo][MAC] Fix the issue that python demo and cxx_demo failed on MAC env · 7953f893
  由 huzhiqiang 提交于 5月 13, 2020
  
  7953f893
- H
  
  [X86][Demo][MAC] Fix the issue that python demo and cxx_demo failed on MAC env · ac3bdf1d
  由 huzhiqiang 提交于 5月 13, 2020
  
  ac3bdf1d
- Z
  
  [NPU] save subgraph model cache (#3589) · aa05c93e
  由 zhupengyang 提交于 5月 13, 2020
  
  aa05c93e
- Z
  
  [NPU] save subgraph model cache (#3589) · 56ea5fff
  由 zhupengyang 提交于 5月 13, 2020
  
  56ea5fff
12 5月, 2020 6 次提交

[LITE][XPU] 1. Add precision switch(int16/int31) in XPUMultiEncoderOp; 2. Fix... · 2db5023d

由 Cwndmiao 提交于 5月 12, 2020

[LITE][XPU] 1. Add precision switch(int16/int31) in XPUMultiEncoderOp; 2. Fix identity_dropout_eliminate_pass, |AttrType| of 'is_test' in OpDesc can be INT or BOOLEAN; 3. Enhance |__xpu__multi_encoder_fuse_pass|; (#3596)

* [LITE][XPU] Add precision switch(int16/int31) in XPUMultiEncoderOp

* [LITE][XPU] fix identity_dropout_eliminate_pass, |AttrType| of 'is_test' in OpDesc can be INT or BOOLEAN

* test=develop

* [LITE][XPU] suppress linkage error
test=develop

* [LITE][XPU] 1. Reorder |identity_dropout_eliminate_pass| before |__xpu__multi_encoder_fuse_pass|; 2. Enhance |__xpu__multi_encoder_fuse_pass|, it works well in more scenarios;
test=develop

* [LITE][XPU] Remove XPUConfig
test=develop

2db5023d

[LITE][XPU] 1. Add precision switch(int16/int31) in XPUMultiEncoderOp; 2. Fix... · ca51f68f

由 Cwndmiao 提交于 5月 12, 2020

[LITE][XPU] 1. Add precision switch(int16/int31) in XPUMultiEncoderOp; 2. Fix identity_dropout_eliminate_pass, |AttrType| of 'is_test' in OpDesc can be INT or BOOLEAN; 3. Enhance |__xpu__multi_encoder_fuse_pass|; (#3596)

* [LITE][XPU] Add precision switch(int16/int31) in XPUMultiEncoderOp

* [LITE][XPU] fix identity_dropout_eliminate_pass, |AttrType| of 'is_test' in OpDesc can be INT or BOOLEAN

* test=develop

* [LITE][XPU] suppress linkage error
test=develop

* [LITE][XPU] 1. Reorder |identity_dropout_eliminate_pass| before |__xpu__multi_encoder_fuse_pass|; 2. Enhance |__xpu__multi_encoder_fuse_pass|, it works well in more scenarios;
test=develop

* [LITE][XPU] Remove XPUConfig
test=develop

ca51f68f

Z

[NPU] share buffer between lite tensor and npu tensor (#3606) · a66b29d7
由 zhupengyang 提交于 5月 12, 2020

a66b29d7
Z

[NPU] share buffer between lite tensor and npu tensor (#3606) · b2142d4a
由 zhupengyang 提交于 5月 12, 2020

b2142d4a
H

[Framwork][InferShape]Improve InferShape period (#3601) · ddc57565
由 huzhiqiang 提交于 5月 12, 2020

ddc57565
H

[Framwork][InferShape]Improve InferShape period (#3601) · a39a1aef
由 huzhiqiang 提交于 5月 12, 2020

a39a1aef

11 5月, 2020 2 次提交

add the document of compileing lite on windows (#3471) · 72f97cae

由 silingtong123 提交于 5月 11, 2020

* test=develop, support WITH_TESTING=ON on windows

test=develop, modify the path of test_file in build_windows.bat

test=develop, modify the docment of windows compilation

test=develop, modify the document

* test=develop, modify the build_windows.bat

72f97cae

add the document of compileing lite on windows (#3471) · 6554ca3d

由 silingtong123 提交于 5月 11, 2020

* test=develop, support WITH_TESTING=ON on windows

test=develop, modify the path of test_file in build_windows.bat

test=develop, modify the docment of windows compilation

test=develop, modify the document

* test=develop, modify the build_windows.bat

6554ca3d

08 5月, 2020 6 次提交
- H
  
  [BUGFIX][Hash] Improve the implementation of hash_combine #3573 · cd1192aa
  由 huzhiqiang 提交于 5月 08, 2020
  
  cd1192aa
- H
  
  [BUGFIX][Hash] Improve the implementation of hash_combine #3573 · f5a7df25
  由 huzhiqiang 提交于 5月 08, 2020
  
  f5a7df25
- W
  add eltwise_activate fuse. test=develop (#3367) · 052e5174
  由 Wilber 提交于 5月 08, 2020
```
* add eltwise_activate_fuse. test=develop
```
  052e5174
- W
  add eltwise_activate fuse. test=develop (#3367) · 2a344823
  由 Wilber 提交于 5月 08, 2020
```
* add eltwise_activate_fuse. test=develop
```
  2a344823
- Y
  [LITE][PROFILE] Fix Precison Profiler caused by X86 header (#3506) · 522a9ee7
  由 Yuan Shuai 提交于 5月 08, 2020
```
* [LITE] Set high perf mode as default in mobile_light deme; Fix Precision Profiler caused by X86 header; Enhance profiler for opencl. test=develop
```
  522a9ee7
- Y
  [LITE][PROFILE] Fix Precison Profiler caused by X86 header (#3506) · 06f77998
  由 Yuan Shuai 提交于 5月 08, 2020
```
* [LITE] Set high perf mode as default in mobile_light deme; Fix Precision Profiler caused by X86 header; Enhance profiler for opencl. test=develop
```
  06f77998
06 5月, 2020 2 次提交

[LITE][BM] support hd all models,test=develop (#3540) · 92d4172a

由 Santa An 提交于 5月 06, 2020

 fix reshape infer shape issue  
adaptive pool, 
support adaptive pool2,  
multi thread ok,   
optimize global pool, 
support faceboxes and behavior image, 
realize bm device info, 
multi device ok, 
support multi cards, 
support efficienet

92d4172a

[LITE][BM] support hd all models,test=develop (#3540) · 94416b2c

由 Santa An 提交于 5月 06, 2020

 fix reshape infer shape issue  
adaptive pool, 
support adaptive pool2,  
multi thread ok,   
optimize global pool, 
support faceboxes and behavior image, 
realize bm device info, 
multi device ok, 
support multi cards, 
support efficienet

94416b2c