- 31 1月, 2019 19 次提交
-
-
由 Tao Luo 提交于
optimize density_prior_box_op.h in detect model for cpu
-
由 Yan Chunwei 提交于
-
由 Jiabin Yang 提交于
test=develop, fast_install shell for linux and mac
-
由 Cheerego 提交于
* update_readme * test=develop
-
由 Guo Sheng 提交于
To make CUDA_LAUNCH_KERNEL_HELPER support large size.
-
由 JiabinYang 提交于
-
-
由 dzhwinter 提交于
-
由 qingqing01 提交于
-
由 liuwei1031 提交于
* expose peak gpu memory API to python test=develop * add unittest for peak gpu memory monitoring test=develop * add pybind change test=develop * add mutex to gpu mem usage monitor test=develop * update benchmark flag definition file test=develop * tweak unittest for memory monitoring test=develop
-
由 jerrywgz 提交于
Add box clip op
-
由 mozga-intel 提交于
test=develop
-
由 tensor-tang 提交于
refine bert
-
由 jerrywgz 提交于
-
由 JiabinYang 提交于
-
由 guoshengCS 提交于
test=develop
-
由 Yan Chunwei 提交于
-
由 Yan Chunwei 提交于
-
由 lidanqing-intel 提交于
test=develop
-
- 30 1月, 2019 21 次提交
-
-
由 tensor-tang 提交于
* use mat attr and refine test test=develop * add matmul jitcode test=develop * fix mac compile test=develop
-
由 JiabinYang 提交于
-
由 JiabinYang 提交于
-
-
由 Haihao Shen 提交于
* Add calibration README; test=develop
-
由 jerrywgz 提交于
-
由 Xin Pan 提交于
Yolo loss darknet
-
由 shanyi15 提交于
-
由 Tao Luo 提交于
use embedding=128 bert model for test
-
由 shanyi15 提交于
-
https://github.com/JiabinYang/Paddle由 shanyi15 提交于
Merge branch 'fast_install_1.3' of https://github.com/JiabinYang/Paddle into JiabinYang-fast_install_1.3
-
由 JiabinYang 提交于
-
-
由 Haihao Shen 提交于
* Add INT8 calibration support in Paddle package; test=develop
-
-
由 mozga-intel 提交于
* Enable pool2d operator for a ngraph engine test=develop * Update test=develop
-
由 Jiabin Yang 提交于
test=develop, polish code and fix some wrong change
-
由 tangwei12 提交于
* move var strusted to vars_distributed.py, add optimizer's block name, test=develop * rename optimzier's seems complex, revert it, test=develop * replace * with details, test=develop
-
由 Haihao Shen 提交于
* Enable performance measurement in INT8 calibration unit test
-
由 chengduo 提交于
test=develop
-
由 Tao Luo 提交于
Make separate folders for mkldnn codes
-