Commit Graph

81 Commits (19749d52348669cbf2cd000a67b2ffe790384e8c)

Author SHA1 Message Date
hedaoyuan 2b202f754b Optimize maxPoolForward.
9 years ago
Zhaolong Xing a91efdde69
Merge pull request #6177 from NHZlX/add_prelu_neon
9 years ago
xzl fac96456c2 add prelu neon impl
9 years ago
guosheng fe6af6b6ac Enhance the AvgPooling to support optional exclude-mode
9 years ago
hedaoyuan 562599ecf0
Merge pull request #5252 from hedaoyuan/inference
9 years ago
xzl 0b9c4cd7e5 fix comments
9 years ago
xzl a54565ea01 delete mask pool interface from poolprojection
9 years ago
hedaoyuan 6a14f52d4b Remove SharedCpuMatrix in mobile inference.
9 years ago
xzl afa690243e add cuda and cpu pool_forward_with_mask impl
9 years ago
Yi Wang 4558807c48 Use PADDLE_WITH_CUDA instead of PADDLE_WITH_GPU
9 years ago
Yu Yang 84500f9487 Change `PADDLE_ONLY_CPU` to `PADDLE_WITH_GPU`
9 years ago
Luo Tao 780e26826d remove unused CHECK in matrix.cpp
9 years ago
Luo Tao 8067a42bef refine avg-pooling, which is exclusive. refine related code.
9 years ago
Liu Yiqun 8e5f54320f Refine the toolchain file of Android to use clang as default compiler.
9 years ago
Liu Yiqun 50c63dc9e7 Merge branch 'develop' into build_android_clang
9 years ago
chengduoZH 6374831966 fix conflict
9 years ago
chengduoZH b1c0bad9fe Add config parser for pooling3D
9 years ago
Liu Yiqun f241773c4f Support to use clang for Android cross-compiling.
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
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
dangqingqing 1fd00758ac SmoothL1 loss
9 years ago
Liu Yiqun 2ae3dd08f9 Merge branch 'develop' into build_arm
9 years ago
Luo Tao 53da530d90 package avg_gpu_backward
9 years ago
Liu Yiqun f261dc6a8b Merge branch 'develop' into build_arm
9 years ago
Liu Yiqun 6478483f63 Use internal gemm wrapper instead.
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
Liang Zhao e00f06afa4 Add top-k error
9 years ago
xutianbing a948eea3ed clean unused code.
9 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
hedaoyuan 1e6c917ecc fix unit test of paramRelu
10 years ago
xutianbing ec6b13dbfc clean up unused code.
10 years ago
tianbingsz 42e121791e Merge pull request #854 from hedaoyuan/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
hedaoyuan d11e2b4013 Remove some useless code
10 years ago
hedaoyuan 529f24c262 cpu cmrnorm
10 years ago
Yi Wang e9549cbb78 Change "Baidu, Inc" into "PaddlePaddle Authors"
10 years ago
Luo Tao 80c68d38ff clang format .cc .h .cpp .c and .hpp file
10 years ago
xuwei06 bf6f690f31 Add ScalingProjection
10 years ago
Haonan 5591292b7a modifications according to comments
10 years ago
Haonan 069d0004dc multi_binary_cross_entropy when ids vector is provided
10 years ago