Commit Graph

85 Commits (5f5e128d295f2acbda1ee3e8e898a57bb31eed49)

Author SHA1 Message Date
dangqingqing cb6436b50c CPU implementation of row convolution
8 years ago
dangqingqing 6dd90f47c3 Change the size in test_LayerGrad and pass unit test
8 years ago
dangqingqing 1fd00758ac SmoothL1 loss
8 years ago
dangqingqing 2c2947f80e Fix a bug for TransLayer and add unit testing.
8 years ago
Luo Tao e6366e3496 update with comments
8 years ago
Luo Tao 0291c01884 Merge branch 'develop' into stride
8 years ago
Tao Luo 5961b52b13 Merge pull request #1653 from Noplz/normalize-layer
8 years ago
Luo Tao 9298a9ec0d stride pooling for seqlastin and seqfirstin
8 years ago
wangyang59 07c1ea258f python interface for convTransProjection and convTransOperator
8 years ago
wangyang59 b8afb14098 cudnn deconv implememtation
8 years ago
gaoyuan 549cf641cd format the code
8 years ago
Yuan Gao 8c2d1bad7a Merge branch 'develop' into normalize-layer
8 years ago
gaoyuan eb43d93a58 Change Normalize layer to CrossChannelNorm layer
8 years ago
qingqing01 5a933b445e Merge pull request #1592 from Noplz/smooth_l1_layer
8 years ago
Peng Li bf838034d6 Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
gaoyuan 7ff9764fc0 smooth_l1_loss_layer
8 years ago
gaoyuan eea0097dcb NormalizeLayer for SSD
8 years ago
Haonan b9dfe8e7c8 Merge pull request #1231 from yu239/rotate_and_flip
8 years ago
Haonan 73dcf2cd58 improving code comments
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
wangyang59 04b5daf92d change the parameter position of gru_step_layer from 1 back to 0
8 years ago
wangyang59 0bd67524b1 switch the parameter index in GruStepLayer in test_LayerGrad
8 years ago
dangqingqing 74f76e61d8 update code and fix bug
8 years ago
dangqingqing 6b61a096e1 Optional padding mode, namely ceil or floor, ceil by default.
8 years ago
dangqingqing c8817a192b merge upstream
8 years ago
dangqingqing 8b5431d5e1 padding operation
8 years ago
xutianbing 936b0ed118 add paddle_test_util static lib to simplify unit test.
8 years ago
Peng Li af820fb2eb Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
Peng Li f1e31ecada Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
hedaoyuan 9171ab0ac1 Merge branch 'develop' of https://github.com/baidu/Paddle into cmrnorm
8 years ago
liaogang 3d0e73bd32 Remove custom glog-like and gflags-like macros
8 years ago
hedaoyuan 529f24c262 cpu cmrnorm
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 7830893a83 fix conflict
8 years ago
Peng Li 1242e7944b Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
wangyang59 09a5b8bd4d consolidate img_conv.conf in test_NetworkCompare
8 years ago
wangyang59 4641285c75 Added a test in test_NetworkCompare to verify cudnn and exconv, fixed a bug in cudnn_conv in dealing with groups
8 years ago
Peng Li e9c61b67e2 Fix bug in processing instance weight and coeff in CRFLayer
8 years ago
Luo Tao 96615fe329 merge develop, fix conflict
8 years ago
Luo Tao 80c68d38ff clang format .cc .h .cpp .c and .hpp file
8 years ago
Luo Tao 496d64ebdb Support rectangle input for CNN
8 years ago
xuwei06 bf6f690f31 Add ScalingProjection
8 years ago
Haonan 5591292b7a modifications according to comments
8 years ago
Haonan 069d0004dc multi_binary_cross_entropy when ids vector is provided
8 years ago
Tao Luo ca0bb40c6e Merge pull request #300 from QiJune/feature/sppnet
8 years ago
Tao Luo eb3bf9ea64 Merge pull request #360 from emailweixu/sum_cost
8 years ago
qijun 9dd588b414 fix merge conflicts
8 years ago
gangliao 8295eb91bf Merge pull request #287 from gangliao/bilinear
8 years ago