- 11 10月, 2019 1 次提交
-
-
由 Yuan Shuai 提交于
* [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
-
- 10 10月, 2019 4 次提交
-
-
由 Wilber 提交于
* fix yolobox_cuda bug * update code format
-
由 Yanzhan Yang 提交于
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)
-
由 Yuan Shuai 提交于
* [CMAKE] Abandon strip when CMAKE_BUILD_TYPE=Debug * Add CMAKE_BUILD_TYPE info in cmake. test=develop
-
由 xiebaiyuan 提交于
-
- 09 10月, 2019 5 次提交
-
-
由 Yanzhan Yang 提交于
* 1. add quantification_fold parameter. 2. support quantification test in run.py. * implement n-fold quantification
-
由 yiicy 提交于
* imporve prepack_input func speed in int8 3x3s1 dw conv * fix code style * fix code style * improve 3x3s1 dw fp32 conv speed a little * arm add 5x5s1 int8 dw conv, test=develop
-
由 xiebaiyuan 提交于
* 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
-
由 zp7 提交于
-
由 xiebaiyuan 提交于
-
- 08 10月, 2019 1 次提交
-
-
由 Jiaying Zhao 提交于
-
- 01 10月, 2019 1 次提交
-
-
由 sangoly 提交于
-
- 27 9月, 2019 4 次提交
-
-
由 zp7 提交于
-
由 Zhaolong Xing 提交于
* add conv int8 support(in condition which the input or output channel not be the times of 4) add add_kernel for cuda. * can run yolov3 fp32 test=develop * 1. fix bug with yolov3 run test=develop
-
由 sangoly 提交于
-
由 NazgulLee 提交于
-
- 26 9月, 2019 2 次提交
- 25 9月, 2019 6 次提交
-
-
由 Xiaoyang LI 提交于
-
由 Xiaoyang LI 提交于
-
由 StarryRain 提交于
* 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
-
由 Xiaoyang LI 提交于
-
由 Xiaoyang LI 提交于
-
由 juncaipeng 提交于
-
- 24 9月, 2019 1 次提交
-
-
由 Jiaying Zhao 提交于
* fix fpga ci build error. test=develop * fix fpga ci build error. test=develop
-
- 23 9月, 2019 4 次提交
-
-
由 Wilber 提交于
-
由 juncaipeng 提交于
* add cast from uint8 to float, test=develop
-
由 Yan Chunwei 提交于
-
由 Yan Chunwei 提交于
-
- 21 9月, 2019 2 次提交
-
-
由 hong19860320 提交于
-
由 Wilber 提交于
-
- 20 9月, 2019 3 次提交
-
-
由 huzhiqiang 提交于
* fix compiling and fix code style test=develop
-
由 Pei Yang 提交于
-
由 Zhaolong Xing 提交于
test=develop
-
- 19 9月, 2019 5 次提交
-
-
由 石晓伟 提交于
* add full_api_static target and fix building errors, test=develop * fix build errors, test=develop * fix code style, test=develop * fix lite/model_parser/pb/var_desc.cc, test=develop * fix building errors, test=develop * modify lite/tools/debug/CMakeLists.txt, test=develop
-
由 Xiaoyang LI 提交于
* fix building model_optimize_tool error on mac, test=develop * fix model_optimize_tool build error, test=develop
-
由 TianXiaogang 提交于
* fix: fix model parser and save bug * style: delete debug code * fix: fix light_predictor program run model with subblock bug
-
由 huzhiqiang 提交于
(1)modify tiny publish so to make it excutable (2)modify the bug of compiling in armlinux (3)change 3 full publish so into 2
-
由 sangoly 提交于
-
- 18 9月, 2019 1 次提交
-
-
由 石晓伟 提交于
-