Commit Graph

53 Commits (bee95fc8917e09f61ba46586a94d2b9003cddf13)

Author SHA1 Message Date
whs a162ebce8b Merge branch 'develop' into pixel_softmax_layer
9 years ago
chengduoZH 6374831966 fix conflict
9 years ago
chengduoZH 860bf192c9 Add maxPoolIdx
9 years ago
chengduoZH 790379f147 fix above comments
9 years ago
chengduoZH 2377d71947 Add3DPooling
9 years ago
chengduoZH 43f6cdc824 fix Matrix
9 years ago
chengduoZH 52ceeedba5 Add col2vol and vol2col CPU funtion
9 years ago
hedaoyuan ff8262e283 Merge branch 'develop' into ImageExpandFunction
9 years ago
wanghaoshuang 1cdf149b6f 1. delete PixelSoftmaxLayer and add SwitchOrderLayer
9 years ago
wanghaoshuang 29f25fbe03 Add pixel softmax layer for FCN model
9 years ago
hedaoyuan 49e87ee327 Change the CpuMatrix::copyFrom and CpuVector::copyFrom with the stream parameter to the synchronous interface.
9 years ago
hedaoyuan 09d712d6ae Remove useless code(Matrix::convExpand and Matrix::convShrink).
9 years ago
yangyaming 7ee942bba8 Add scale factor for smoothL1 and smoothL1Bp
9 years ago
Luo Tao 53da530d90 package avg_gpu_backward
9 years ago
gaoyuan 7ff9764fc0 smooth_l1_loss_layer
9 years ago
Liang Zhao 8fded24c75 implement top k classification error in class matrix
9 years ago
xutianbing a948eea3ed clean unused code.
10 years ago
Haonan 2558c3f15a revisions according to reviews
10 years ago
Haonan 781b85b5fc rotate_layer and flip_layer * added getMin and getMax for GpuMatrix * gru_step_layer parameter name
10 years ago
xutianbing 999cd14a6e Further address Daoyuan's comments, clean the code.
10 years ago
hedaoyuan ee2da539de Merge branch 'develop' of https://github.com/baidu/Paddle into buffer
10 years ago
hedaoyuan 41c52d3b0c Modify the argument type of ContextProjectionFunc
10 years ago
liaogang be8b126845 Move Execepts into arch/osx dir
10 years ago
xutianbing ec6b13dbfc clean up unused code.
10 years ago
liaogang c8d0791acc Add common.h and remove DisableCopy and Typedefs
10 years ago
tianbingsz 42e121791e Merge pull request #854 from hedaoyuan/cmrnorm
10 years ago
hedaoyuan bf32411191 Merge branch 'develop' of https://github.com/baidu/Paddle into cmrnorm
10 years ago
xutianbing 4fbf94993b Refactor MUL functions, pass object reference instead of shared_ptr.
10 years ago
xutianbing 706c572424 Matrix API refactor, when passing parameters, convert shared_ptr (MatrixPtr) to
10 years ago
Yu Yang af5d954bdf Clean BatchNorm Code.
10 years ago
hedaoyuan d11e2b4013 Remove some useless code
10 years ago
hedaoyuan bf47397125 Merge pull request #859 from hedaoyuan/fix_warning
10 years ago
hedaoyuan 4736246515 fix warning
10 years ago
Yu Yang 068bfbb817 All file pass pre-commit hook
10 years ago
Yi Wang e9549cbb78 Change "Baidu, Inc" into "PaddlePaddle Authors"
10 years ago
hedaoyuan 671db8deaa Merge branch 'develop' of https://github.com/baidu/Paddle into tensor_merge
10 years ago
hedaoyuan e63f1e6952 merge from cooder
10 years ago
Luo Tao 80c68d38ff clang format .cc .h .cpp .c and .hpp file
10 years ago
Haonan 069d0004dc multi_binary_cross_entropy when ids vector is provided
10 years ago
gangliao 8295eb91bf Merge pull request #287 from gangliao/bilinear
10 years ago
Liang Zhao 992ac8f9a1 Implement setDiag() with BaseMatrix::assign()
10 years ago
Liang Zhao 8c40bfd0fc Make matrix well-conditioned when unittest inverse
10 years ago
liaogang db1757556e Follow comments
10 years ago
liaogang bd38facada Fix conflict
10 years ago
lzhao4ever 5f2059db05 Add matrix inverse (#240)
10 years ago
qingqing01 45c81a414f Add job=time in trainer, refine cudnn_conv to reduce gpu memory and speed up training. (#218)
10 years ago
liaogang fd4eeaf59c Merge conflict with maxout layer
10 years ago
liaogang ddfff3a7fd Add bilinear interpolation layer
10 years ago
luotao1 3dd8c9bea4 add maxout layer, including interface and unittest (#229)
10 years ago
luotao1 91df606280 remove some copyfrom in AgentLayer and ExpandLayer, fix warning in seq2seq config (#183)
10 years ago