Commit Graph

17 Commits (58561d8f56b9f5436a12f42994ece7481bde8f9d)

Author SHA1 Message Date
hedaoyuan 74f8ede976 Fix when use_nnpack and isDeconv == true.
8 years ago
xzl 1f516fa0ef modify format, and modify the layer grad test, op test
8 years ago
xzl 81998868f0 fuse interface of depthwise to expandconv
8 years ago
hedaoyuan 47f1031fb7 Modify the type of alog parameter.
8 years ago
hedaoyuan b5514602b6 Add the use_nnpack parameter in ExpandConvLayer, so that the convolution calculation can be switched to the NNPACK function.
8 years ago
hedaoyuan 784e21848f Fix the error of group convolution.
8 years ago
hedaoyuan 7aac38c794 Refactoring the code implementation of exconv adn exconvt layer with GemmConvFunction.
8 years ago
Yu Yang 068bfbb817 All file pass pre-commit hook
8 years ago
Yi Wang e9549cbb78 Change "Baidu, Inc" into "PaddlePaddle Authors"
8 years ago
Luo Tao 80c68d38ff clang format .cc .h .cpp .c and .hpp file
8 years ago
wangyang59 af7a50c0d4 minor changes on deconv implementation and add protostr test for deconv layer
9 years ago
wangyang59 3d72e94939 rebase deconv implementation with develop branch and resolve conflicts with pull#218 commit 45c81a414f
9 years ago
wangyang59 5e4cc241ac Revised deconv implementations according to luotao1
9 years ago
wangyang59 2575b74fee refactored ExpandConvLayer and ExpandConvTransLayer with ConvBaseLayerCpu
9 years ago
wangyang59 aa2cd2ce8f Refactor ExpandConvTransLayer to share codes with ExpandConvLayer
9 years ago
qingqing01 45c81a414f Add job=time in trainer, refine cudnn_conv to reduce gpu memory and speed up training. (#218)
9 years ago
zhangjinchao01 b72beee4f0 fix dash and space bug,
9 years ago