Commit Graph

54 Commits (8106f414f7403442d2e9191a231ed965c4d39b98)

Author SHA1 Message Date
xzl afa690243e add cuda and cpu pool_forward_with_mask impl
7 years ago
whs a162ebce8b Merge branch 'develop' into pixel_softmax_layer
8 years ago
chengduoZH 6374831966 fix conflict
8 years ago
chengduoZH 860bf192c9 Add maxPoolIdx
8 years ago
chengduoZH 790379f147 fix above comments
8 years ago
chengduoZH 2377d71947 Add3DPooling
8 years ago
chengduoZH 43f6cdc824 fix Matrix
8 years ago
chengduoZH 52ceeedba5 Add col2vol and vol2col CPU funtion
8 years ago
hedaoyuan ff8262e283 Merge branch 'develop' into ImageExpandFunction
8 years ago
wanghaoshuang 1cdf149b6f 1. delete PixelSoftmaxLayer and add SwitchOrderLayer
8 years ago
wanghaoshuang 29f25fbe03 Add pixel softmax layer for FCN model
8 years ago
hedaoyuan 49e87ee327 Change the CpuMatrix::copyFrom and CpuVector::copyFrom with the stream parameter to the synchronous interface.
8 years ago
hedaoyuan 09d712d6ae Remove useless code(Matrix::convExpand and Matrix::convShrink).
8 years ago
yangyaming 7ee942bba8 Add scale factor for smoothL1 and smoothL1Bp
8 years ago
Luo Tao 53da530d90 package avg_gpu_backward
8 years ago
gaoyuan 7ff9764fc0 smooth_l1_loss_layer
8 years ago
Liang Zhao 8fded24c75 implement top k classification error in class matrix
8 years ago
xutianbing a948eea3ed clean unused code.
8 years ago
Haonan 2558c3f15a revisions according to reviews
8 years ago
Haonan 781b85b5fc rotate_layer and flip_layer * added getMin and getMax for GpuMatrix * gru_step_layer parameter name
8 years ago
xutianbing 999cd14a6e Further address Daoyuan's comments, clean the code.
8 years ago
hedaoyuan ee2da539de Merge branch 'develop' of https://github.com/baidu/Paddle into buffer
8 years ago
hedaoyuan 41c52d3b0c Modify the argument type of ContextProjectionFunc
8 years ago
liaogang be8b126845 Move Execepts into arch/osx dir
8 years ago
xutianbing ec6b13dbfc clean up unused code.
8 years ago
liaogang c8d0791acc Add common.h and remove DisableCopy and Typedefs
8 years ago
tianbingsz 42e121791e Merge pull request #854 from hedaoyuan/cmrnorm
8 years ago
hedaoyuan bf32411191 Merge branch 'develop' of https://github.com/baidu/Paddle into cmrnorm
8 years ago
xutianbing 4fbf94993b Refactor MUL functions, pass object reference instead of shared_ptr.
8 years ago
xutianbing 706c572424 Matrix API refactor, when passing parameters, convert shared_ptr (MatrixPtr) to
8 years ago
Yu Yang af5d954bdf Clean BatchNorm Code.
8 years ago
hedaoyuan d11e2b4013 Remove some useless code
8 years ago
hedaoyuan bf47397125 Merge pull request #859 from hedaoyuan/fix_warning
8 years ago
hedaoyuan 4736246515 fix warning
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
hedaoyuan 671db8deaa Merge branch 'develop' of https://github.com/baidu/Paddle into tensor_merge
8 years ago
hedaoyuan e63f1e6952 merge from cooder
8 years ago
Luo Tao 80c68d38ff clang format .cc .h .cpp .c and .hpp file
8 years ago
Haonan 069d0004dc multi_binary_cross_entropy when ids vector is provided
8 years ago
gangliao 8295eb91bf Merge pull request #287 from gangliao/bilinear
8 years ago
Liang Zhao 992ac8f9a1 Implement setDiag() with BaseMatrix::assign()
8 years ago
Liang Zhao 8c40bfd0fc Make matrix well-conditioned when unittest inverse
8 years ago
liaogang db1757556e Follow comments
8 years ago
liaogang bd38facada Fix conflict
8 years ago
lzhao4ever 5f2059db05 Add matrix inverse (#240)
8 years ago
qingqing01 45c81a414f Add job=time in trainer, refine cudnn_conv to reduce gpu memory and speed up training. (#218)
8 years ago
liaogang fd4eeaf59c Merge conflict with maxout layer
8 years ago
liaogang ddfff3a7fd Add bilinear interpolation layer
8 years ago
luotao1 3dd8c9bea4 add maxout layer, including interface and unittest (#229)
8 years ago