提交 · c6d366c2fa6b16b4fbcfda28af7f9485f97aefa2 · PaddlePaddle / Paddle-Lite

13 5月, 2019 2 次提交

fix load_when_predict mode in opencl (#1619) · c6d366c2

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

c6d366c2

update feed fetch and softmax kernel in FPGA v2 track fixed#1615 (#1616) · cf542116

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

cf542116

10 5月, 2019 1 次提交

io+softmax update for FPGA V1 track (#1613) · 542008c0

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

542008c0

09 5月, 2019 1 次提交
- J
  support V1 para equal to 2 (#1609) · 04610db8
  由 jameswu2014 提交于 5月 09, 2019
```
* V2-conv-hellocase pass & V1 verify-pass

* V1 paralvl equal to 2
```
  04610db8
08 5月, 2019 2 次提交

J

V2-conv-hellocase pass & V1 verify-pass (#1608) · 49038a6a
由 jameswu2014 提交于 5月 08, 2019

49038a6a

update io file to surport int8 tensor feed and fetch fixed#1602 (#1603) · ee4b392a

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

ee4b392a

07 5月, 2019 2 次提交

update feed and fetch kernel in FPGA v2 track fixed#1600 (#1601) · 4c7352b1

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

4c7352b1

change funtion name (#1598) · 98ab80cd

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

98ab80cd

06 5月, 2019 1 次提交
- J
  optimize GPU conv performance and structure (#1595) · cf70102b
  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
```
  cf70102b
30 4月, 2019 2 次提交

update kernel and related files for static quantization in FPGA v2 track fixed#1589 (#1590) · ceda3f4e

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

ceda3f4e

Update Build docs for ARM Linux CPU and GPU(OpenCL) (#1583) · 15794c0a

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

15794c0a

29 4月, 2019 1 次提交

update kernel and related files for static quantization in FPGA v2 track fixed#1584 (#1585) · 99cccf3b

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

99cccf3b

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) · 515c42ec
  由 Houjiang Chen 提交于 4月 28, 2019
```
* Fix memory leak if tensor was created outside of global scope

* Fix gemv bugs
```
  515c42ec
25 4月, 2019 5 次提交
- Z
  
  gpu conv_bn_add_relu use 1x1 optimise kernel · 5a2334af
  由 zhaojiaying01 提交于 4月 25, 2019
  
  5a2334af
- Z
  
  format code style · 8dd3ff3a
  由 zhaojiaying01 提交于 4月 25, 2019
  
  8dd3ff3a
- Z
  
  adjust gpu code structure · 44809658
  由 zhaojiaying01 提交于 4月 25, 2019
  
  44809658
- Z
  
  format code style · 93c3df7b
  由 zhaojiaying01 提交于 4月 25, 2019
  
  93c3df7b
- Z
  
  fix gpu conv_kernel · eebe855a
  由 zhaojiaying01 提交于 4月 25, 2019
  
  eebe855a
24 4月, 2019 1 次提交

Give advice for Alloc function users (#1575) · e6f8c6c9

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

e6f8c6c9

23 4月, 2019 2 次提交
- H
  
  Fix compilation on Raspberry PI3, and fix some code style (#1566) · d63ba688
  由 Houjiang Chen 提交于 4月 23, 2019
  
  d63ba688
- S
  BugFix: fix multi-threadings incorrectness of cpu gemm (#1569) · 94fb88b4
  由 Shuai Yuan 提交于 4月 23, 2019
```
* BugFix: fix multi-threadings incorrectness of cpu gemm

* BugFix: fix lack of header file for memset

* BugFix: fix lacking of header file for memset
```
  94fb88b4
22 4月, 2019 2 次提交
- update some files related with static quantization in FPGA V2 track · c72044e0
  由 qnqinan 提交于 4月 22, 2019
  
  c72044e0
- C
  FPGA refactor #1560 (#1561) · 3f1e8f7d
  由 Chon 提交于 4月 22, 2019
```
* FPGA refactor

* disable FPGAKD

* recover misdeleted code segment
```
  3f1e8f7d
19 4月, 2019 3 次提交
- update · d16525f7
  由 qnqinan 提交于 4月 19, 2019
  
  d16525f7
- update some files in FPGA V2 · 538ca2ce
  由 qnqinan 提交于 4月 19, 2019
  
  538ca2ce
- add static quantization code and update FPGA V2(V3) related files · 59bdbff9
  由 qnqinan 提交于 4月 19, 2019
  
  59bdbff9
15 4月, 2019 1 次提交

Add fetch API for java, refine android log (#1558) · 8505700f

由 Houjiang Chen 提交于 4月 15, 2019

* Clear no persistable tensor array before predicting, fix crash when predicting with gpu debugging mode

* Fix code style

* Add fetch API for java, refine android log

8505700f

12 4月, 2019 1 次提交

Fix Multi-threading incorrectness of NEON armv7 gemv_trans_mx1 (#1556) · 563f0cc5

由 Shuai Yuan 提交于 4月 12, 2019

* add prepare data and model script, modified corresponding docs:development_android and development_android_GPU

* Add verified multi-threading supported gemv_trans_mx1

* add comments for alloc and free

* optimize reduction progress of gemv_trans_mx1

* add macro for gemv_trans_mx1

* Fix multi-threadings incorrectnesss of armv7 neon gemv_trans_mx1

* add test_gemm_accuracy

563f0cc5

04 4月, 2019 1 次提交

Clear no persistable tensor array before predicting, fix crash when predicting... · 04c139b9

由 Houjiang Chen 提交于 4月 04, 2019

Clear no persistable tensor array before predicting, fix crash when predicting with gpu debugging mode (#1548)

* Clear no persistable tensor array before predicting, fix crash when predicting with gpu debugging mode

* Fix code style

04c139b9

01 4月, 2019 1 次提交
- Z
  
  modify FPGA doc · 1abb398c
  由 zhangyang0701 提交于 4月 01, 2019
  
  1abb398c
30 3月, 2019 1 次提交
- H
  
  improve program optimize, add assign value and flatten2 op · 63df3091
  由 hjchen2 提交于 3月 30, 2019
  
  63df3091
29 3月, 2019 3 次提交
- H
  
  Fix unit test · 65a8b291
  由 hjchen2 提交于 3月 29, 2019
  
  65a8b291
- H
  
  Make fpga/gpu compiles, and disable memory optimize if compiled with gpu · 294e346f
  由 hjchen2 提交于 3月 29, 2019
  
  294e346f
- H
  
  Use enum type rather than string since comparing between enum is more efficent than string · 7701ac0d
  由 hjchen2 提交于 3月 29, 2019
  
  7701ac0d
28 3月, 2019 2 次提交
- H
  
  Replace C++ typeid with self-defined type_id to avoid implementation difference · 6fd788f7
  由 hjchen2 提交于 3月 28, 2019
  
  6fd788f7
- J
  
  anchor_generator+version · 7bc50fb6
  由 jameswu2014 提交于 3月 28, 2019
  
  7bc50fb6
26 3月, 2019 2 次提交
- update · 94baa91e
  由 qnqinan 提交于 3月 26, 2019
  
  94baa91e
- clean interrupt signal at the beginning of bypass in FPGA track · 83ba1b39
  由 qnqinan 提交于 3月 26, 2019
  
  83ba1b39
21 3月, 2019 2 次提交
- H
  
  Fix bugs in multi-threads sgemm and fuse conv/add/bn/relu · 288148fe
  由 hjchen2 提交于 3月 21, 2019
  
  288148fe
- update · 883692c4
  由 qnqinan 提交于 3月 21, 2019
  
  883692c4