Commit Graph

231 Commits (397dcf0dbaefabbcfc728188011aee9663bd3da0)

Author SHA1 Message Date
liaogang c8d0791acc Add common.h and remove DisableCopy and Typedefs
8 years ago
Yu Yang 2016f9222d Merge pull request #989 from gangliao/utils_dep
8 years ago
Peng Li 89bf2e44f0 Change float to real in NormLayer.h
8 years ago
liaogang f09989a1b2 Remove utils/CommandLineParser.h
8 years ago
qingqing01 b53bdcdc67 Merge pull request #867 from Noplz/ssd
8 years ago
Peng Li 3527939896 Fix merge and style error
8 years ago
gaoyuan 8d24931588 Change member variables from public to protected
8 years ago
Peng Li af820fb2eb Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
gaoyuan f2029298a7 Change type float to real.
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
Peng Li f1e31ecada Merge branch 'develop' into fix-crf-weight-and-coeff-bug
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
hedaoyuan 148bd4d0b3 add Layer::createFunction
8 years ago
Yu Yang af5d954bdf Clean BatchNorm Code.
8 years ago
gaoyuan 9f990d9059 Add unittest of the priorbox layer
8 years ago
qingqing01 bd3f976a85 Merge pull request #906 from emailweixu/check_cnn_input_size
8 years ago
xuwei06 7462692d4c Formatted by pre-commit
8 years ago
hedaoyuan cee9346804 add some comments
8 years ago
hedaoyuan d11e2b4013 Remove some useless code
8 years ago
hedaoyuan 22a5e478f3 move Function to function dir
8 years ago
hedaoyuan d2d0010609 add CrossMapNormalGradFunc
8 years ago
gaoyuan 520342ed91 Fix code format
8 years ago
gaoyuan 707a9c9bbd Fix variable name and add the annotation
8 years ago
hedaoyuan 9171ab0ac1 Merge branch 'develop' of https://github.com/baidu/Paddle into cmrnorm
8 years ago
hedaoyuan 4ebb3eb759 imporve Function
8 years ago
gangliao 6aed264f0a Merge pull request #896 from gangliao/glog
8 years ago
xuwei06 bcd280d6bd Check the input size for convolution.
8 years ago
Zhizhong Su 9a243d7a23 fix a few bugs related to frame size.
8 years ago
liaogang 3d0e73bd32 Remove custom glog-like and gflags-like macros
8 years ago
gaoyuan 9600932650 Add fake gpu support of the priorbox layer for the moment
8 years ago
gaoyuan 39d689e253 Format the priorbox code
8 years ago
yuan 0eac399280 priorbox layer for ssd
8 years ago
Yu Yang f62f5181f1 Use explicit type for std::transform.
8 years ago
Yu Yang d5c0eeda00 Remove m4 when generate protobuf
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
Yiqun Liu 4823075f95 Merge pull request #651 from Xreki/warpctc
8 years ago
Liu Yiqun 78bdd32471 Merge branch 'develop' into warpctc
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
Liu Yiqun 46ef2bc694 Merge branch 'develop' into warpctc
8 years ago
Luo Tao 7830893a83 fix conflict
8 years ago
Peng Li 62eaa1fbab Move one line with identical value across loops out of the loop.
8 years ago
Peng Li 1242e7944b Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
Liu Yiqun 25f1fbc491 Merge branch 'develop' into warpctc
8 years ago
wangyang59 70b78b74ff fix a bug in BatchNormBaseLayer.cpp and add a test for it
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
9 years ago
wangyang59 60bf1a476a Modifed ExpandConvBaseLayer to unify paras between expand and cudnn
9 years ago
Peng Li e9c61b67e2 Fix bug in processing instance weight and coeff in CRFLayer
9 years ago
Liu Yiqun a816443e11 Add submodule warp-ctc.
9 years ago
Luo Tao 1d1a04c033 follow comments on rectangle CNN
9 years ago
Liu Yiqun 4d487c6f35 Integrate warp-ctc as WarpCTCLayer, including unitest and layer interface.
9 years ago
Luo Tao 96615fe329 merge develop, fix conflict
9 years ago
Luo Tao 80c68d38ff clang format .cc .h .cpp .c and .hpp file
9 years ago
Luo Tao 496d64ebdb Support rectangle input for CNN
9 years ago
Yu Yang 9115ab1c11 Merge pull request #450 from reyoung/feature/pre-commit-hooks-scripts
9 years ago
xuwei06 a6ad9a1608 Fix unittest
9 years ago
xuwei06 bf6f690f31 Add ScalingProjection
9 years ago
dangqingqing 48ea047100 Bug fix in testing mode.
9 years ago
Yu Yang 836d61382f Update pre-commit-config
9 years ago
Haonan 5591292b7a modifications according to comments
9 years ago
Haonan 728defbec9 copy the data when createSparseMatrix
9 years ago
Haonan 069d0004dc multi_binary_cross_entropy when ids vector is provided
9 years ago
Tao Luo ca0bb40c6e Merge pull request #300 from QiJune/feature/sppnet
9 years ago
Tao Luo eb3bf9ea64 Merge pull request #360 from emailweixu/sum_cost
9 years ago
qijun 9dd588b414 fix merge conflicts
9 years ago
gangliao 8295eb91bf Merge pull request #287 from gangliao/bilinear
9 years ago
wangyang59 af7a50c0d4 minor changes on deconv implementation and add protostr test for deconv layer
9 years ago
wangyang59 53e1629a43 Refactored imageSize in ConvBaseLayer to MathUtil
9 years ago
wangyang59 7a322df0a8 deconv implementation mionr changes in ConvBaseLayer.cpp and config_parser.py
9 years ago
wangyang59 fb20187aaa deconv layer implementation modification following luotao1 comments
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 e68b50ad09 fixed a bug in refactoring ExpandConv/TransLayer
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
wangyang59 bda259bb18 added more test on convTrans layer and comments
9 years ago
wangyang59 5c88f07262 initial take on deconv layers
9 years ago
qijun dfbde28ad3 add some code comments for SppLayer
9 years ago
qijun eaf3dec9c5 follow comments
9 years ago
qijun 70e04683dd add getSize method for PoolProjection
9 years ago
qijun e2c0713589 follow comments
9 years ago
liaogang db1757556e Follow comments
9 years ago
qijun db569f293e fix merge conflict
9 years ago
qijun 5ece5c96ad add python wrap for sppLayer
9 years ago
xuwei06 38764bf908 Add sum_cost to document
9 years ago
xuwei06 ebad8e525d Add SumCost
9 years ago
liaogang 5a1e7dbc6a Fix conflict
9 years ago
luotao1 e802471c58 abstract outputSize function in CNN-related layers (#314)
9 years ago
liaogang 45b8c47e04 Add img_size for unit test
9 years ago
liaogang bd38facada Fix conflict
9 years ago
liaogang 57348806b5 Follow comments
9 years ago
qijun b282caf4f6 Merge remote-tracking branch 'baidu/develop' into feature/sppnet
9 years ago
qingqing01 5acf136615 Bug fix in CudnnConvLayer, which will lead to destruction error. (#317)
9 years ago
qijun 766a61c374 fix conflict with baidu/develop
9 years ago
qijun fcf177fc4b reuse code of PoolProjection in PoolProjectionLayer
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
qijun cdac60f616 add SpatialPyramidPoolLayer c++ support
9 years ago
liaogang fd4eeaf59c Merge conflict with maxout layer
9 years ago
liaogang ddfff3a7fd Add bilinear interpolation layer
9 years ago
gangliao 9c5c38fa2a FIx check type unmatch in MaxOutLayer (#242)
9 years ago
luotao1 3dd8c9bea4 add maxout layer, including interface and unittest (#229)
9 years ago
luotao1 e1f57bfd66 add base class for seqlastin/max/average layer (#187)
9 years ago
luotao1 91df606280 remove some copyfrom in AgentLayer and ExpandLayer, fix warning in seq2seq config (#183)
9 years ago
luotao1 cebdb66768 hierarchical rnn document, add new config example (#106)
9 years ago
luotao1 43f7d7b768 add interface and unittest for nce layer (#180)
9 years ago
qingqing01 191fafe355 support rectangle padding, stride, window and input for PoolProjection (#115)
9 years ago
hedaoyuan b52039bd11 some bug fix for sparse matrix (#133)
9 years ago
emailweixu b15a4783cb Correctly handling multiple inputs and integer inputs for recurrent_g… (#114)
9 years ago
liuyuan 2289c141c2 Refine comment for CRF related headers. (#117)
9 years ago
qingqing01 c1c07bbef6 Update CudnnConvLayer.cpp
9 years ago
dangqingqing 95da095d10 fix cudnn conv bug which occurs in image classfication demo in GTX GPU
9 years ago
Yu Yang 7eb29f264b Try to fix MultinomialSampler (#102)
9 years ago
Yu Yang 2c5a6ac095 Optional fields to shrink generated proto size (#93)
9 years ago
xuwei06 05a97ab50e Further fix the memory for Hierarchical RNN
9 years ago
Yu Yang c7762da330 Merge branch 'master' into merge_icode
9 years ago
Haonan 0f91ea7ebb use HPPL_STREAM_DEFAULT for layer computation
9 years ago
Haonan 688eeefab3 fixed issues with synchronizing streams when copy from gpu to cpu
9 years ago
xuwei06 7481429f99 Change cos_sim to use CosSimLayer layer when size=1 and rename convex_comb_layer to linear_comb_layer
9 years ago
qingqing01 7dbc092c87 fix cudnn version number for batch norm. (#71)
9 years ago
qingqing01 dcd87fd689 fix CUDNN_VERSION for backward of CudnnBatchNormLayer (#61)
9 years ago
Yu Yang fbfd24e6d9 revert CRFLayer, remove wrong gpu support
9 years ago
liaogang 291318e5a2 delete Bits.h and move its func into utils/Util.h
9 years ago
dangqingqing 54d4968d38 Refine code and comments for CRMNormLayer.
9 years ago
qijun 66be6fed34 add some source code comments
9 years ago
luotao02 260c734c95 fix bug in trainer_config_helpers
9 years ago
dangqingqing 9c0895ee45 Add commits for recurrent layer and lstm layer.
9 years ago
dangqingqing f063752366 Adjustment doc and code for CostLayer, GradientMachine and DataProvider.
9 years ago
zhangjinchao01 b72beee4f0 fix dash and space bug,
9 years ago