0f4c733296
add ROIPooling for Fast(er) R-CNN
8 years ago
ec236f4624
fix code format
8 years ago
1cdf149b6f
1. delete PixelSoftmaxLayer and add SwitchOrderLayer
...
2. Make SwitchOrderLayer support for softmax activation
3. Fix bugs
8 years ago
de5ded6bbd
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer
8 years ago
45adbfc4e0
Merge remote-tracking branch 'origin/develop' into lr_state
8 years ago
5e6e1f636a
Add grad test and python wrapper for crop layer
8 years ago
312ce8b419
Merge pull request #2497 from pkuyym/ssd_outloss
...
Add DetectionOutputLayer and MultiBoxLossLayer.
8 years ago
7edabe74d4
"polish name convention"
8 years ago
e1acd73fab
"fix typo deleted part"
8 years ago
6935dd7bc9
"lr state serialization"
8 years ago
2d3c186a96
Follow comments
8 years ago
4a4ec31e0d
Fix TravisCI
8 years ago
b88ca542ba
Rename pb_cc_library -> proto_library
8 years ago
456f9cc89f
Remove Python protobuf function
8 years ago
64b78b1656
Fix TravisCI
8 years ago
30b75a5103
Also add pb_py_library
8 years ago
b1a311c44d
Add pb_cc_library in generic.cmake
...
Fix #2567
8 years ago
561c4562cf
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
f551c271af
Merge pull request #2467 from pkuyym/ssd_map
...
Add DetectionMAPEvaluator
8 years ago
15bf6e05b5
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
d9aac1e13d
add WITH_Go to disable compile go to paddle
8 years ago
baef96e1da
Merge branch 'develop' into optimizer_lib2
8 years ago
ec65fa835c
"protobuf required to optional"
8 years ago
65d9e33b42
"modify config name"
8 years ago
65969dad64
Add DetectionOutputLayer and MultiBoxLossLayer.
8 years ago
fc9e3e4bda
explain the sparsity ratio
8 years ago
23b1a27483
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
b72e8aa3c6
"seperate serialization proto state"
8 years ago
597a58c3ef
Add DetectionMAPEvaluator.
8 years ago
e4567962fa
"update with comment"
8 years ago
6cbbc2ec1d
"add comments"
8 years ago
81cad37491
"remove comments"
8 years ago
3b1294ae48
"add checkpoint interface: set state, get state"
8 years ago
fd8c51076b
"format name with google style"
8 years ago
5f9cd8c9ae
"rename test file name"
8 years ago
092828fbe3
modify the doc of the interface
8 years ago
5b8a0c5dd8
"optimizer remove init create with proto"
8 years ago
3158efe950
"move cmake scripts too"
8 years ago
18435f2a73
modify the pruning from reading mask to specify sparsity_ratio
8 years ago
5413af8d11
imporve pruning module
8 years ago
cb6436b50c
CPU implementation of row convolution
8 years ago
2e4c0bd2ea
enable global gradient_clipping_threshold
...
correct a typo
optimize code
fix a bug
8 years ago
9298a9ec0d
stride pooling for seqlastin and seqfirstin
8 years ago
e768721cd9
fix calculating totalScore2_ bug
8 years ago
781b85b5fc
rotate_layer and flip_layer * added getMin and getMax for GpuMatrix * gru_step_layer parameter name
8 years ago
a78b65389d
Merge pull request #1230 from helinwang/doc
...
change english documentation for parameter ports_num and ports_num_fo…
8 years ago
cfe0e08663
change english documentation for parameter ports_num and ports_num_for_sparse
8 years ago
47e88f4a2d
update code
8 years ago
aa9f516260
code refine, add comment and some naming problem
8 years ago
c8817a192b
merge upstream
8 years ago
8b5431d5e1
padding operation
8 years ago
b1eeb2e1d7
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add-pserver-util
8 years ago
8acd1ac31a
Add extern python interp
8 years ago
f3c61cbc4c
add pserver util and parameter server config
8 years ago
0b956711d9
Add external_project_dependencies for targets
8 years ago
b53bdcdc67
Merge pull request #867 from Noplz/ssd
...
priorbox layer for Single Shot Multibox Detection Network
8 years ago
6e405a10c5
fix style issues
8 years ago
8fe3a3aa73
Add excluded_chunk_types to ChunkEvaluator
...
The chunks of types in excluded_chunk_types will not be counted in
ChunkEvaluator. This is useful for tasks such as SRL, in which chunks of
type V (verb) will not be taken into account in evaluation.
8 years ago
9a243d7a23
fix a few bugs related to frame size.
8 years ago
c0076084e2
Format the python file.
8 years ago
0eac399280
priorbox layer for ssd
8 years ago
d5c0eeda00
Remove m4 when generate protobuf
...
Also fix compile issues
8 years ago
e9549cbb78
Change "Baidu, Inc" into "PaddlePaddle Authors"
8 years ago
78bdd32471
Merge branch 'develop' into warpctc
8 years ago
7830893a83
fix conflict
8 years ago
25f1fbc491
Merge branch 'develop' into warpctc
8 years ago
d114d8976a
Merge branch 'develop' into conv
8 years ago
1eb9c36fd2
Make ApproximatelyEquals fit for protobuf2
8 years ago
4d487c6f35
Integrate warp-ctc as WarpCTCLayer, including unitest and layer interface.
8 years ago
5b4bec43a6
Add syntax='proto2' when using protobuf 3
8 years ago
7573205c68
follow comments on config_parser
8 years ago
96615fe329
merge develop, fix conflict
8 years ago
4ca9c3955e
minor changes
8 years ago
496d64ebdb
Support rectangle input for CNN
8 years ago
9dd588b414
fix merge conflicts
8 years ago
5ece5c96ad
add python wrap for sppLayer
8 years ago
45b8c47e04
Add img_size for unit test
8 years ago
bd38facada
Fix conflict
8 years ago
57348806b5
Follow comments
8 years ago
b282caf4f6
Merge remote-tracking branch 'baidu/develop' into feature/sppnet
9 years ago
d412a5ea21
add user_arg to LayerConfig ( #315 )
9 years ago
766a61c374
fix conflict with baidu/develop
9 years ago
45c81a414f
Add job=time in trainer, refine cudnn_conv to reduce gpu memory and speed up training. ( #218 )
...
* Add benchmark for PaddlePaddle, tensorflow and caffe
* ConvProjection to reduce memory for goolenet
* Add unit test for ConvProjection.
1. unit test in test_LayerGrad.
2. compare the ConvPorjection and CudnnConvLayer, also compare the concat_layer+img_conv_layer and concat_layer_conv_projection.
* Reduce cudnn_conv memory and add benchmark document.
1. Use TmpMatrix as the workspace in cudnn_conv to reduce gpu memory. It reduce lots of memory.
2. Add benchmark document.
3. fix smallnet_mnist_cifar.py in paddle.
* Add job=time and refine cudnn_conv to reduce gpu memroy and speed up
* Refine cudnn_conv and shared biases operation in concat_layer and mixed_layer.
* follow comments
* follow comments
* Use unique_ptr to prevent memory leaks in CudnnConvLayer.
9 years ago
cdac60f616
add SpatialPyramidPoolLayer c++ support
9 years ago
fd4eeaf59c
Merge conflict with maxout layer
9 years ago
ddfff3a7fd
Add bilinear interpolation layer
9 years ago
cbe734b396
Python trainer api ( #193 )
...
* Python trainer API and demo
* Adding missing PaddleAPIPrivate.h
* Adding api_train.sh
* More comments
* Bump up patch version to 0b3
9 years ago
3dd8c9bea4
add maxout layer, including interface and unittest ( #229 )
...
* add maxout layer, including interface and unittest
* follow maxout comments
* auto setting channels
* fix unittest bug in test_RecurrentGradientMachine
9 years ago
191fafe355
support rectangle padding, stride, window and input for PoolProjection ( #115 )
...
* support rectangle padding, stride, window and input for PoolProjection
* Follow comments.
1. Remove start
2. refine img_pool_a/b.conf for test_NetworkCompare
3. Split unit test
* Modify the test in img_layers.py
9 years ago
2c5a6ac095
Optional fields to shrink generated proto size ( #93 )
...
* remove unnecessary field set in ParameterConfig, Evaluators, etc
9 years ago
699d5f2638
modify RecurrentGradientMachine to support unequal length inputs
...
* modify RecurrentGradientMachine to support hasSubSeq sequence inlinks with the same number of sentence but different number of tokens for each sentence
Change-Id: Ic71f00a4bb346b4fa93e650dfb4b1a0d8d2338b0
9 years ago
b72beee4f0
fix dash and space bug,
...
ISSUE=4586495
git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1408 1ad973e4-5ce8-4261-8a94-b56d1f490c56
9 years ago
guosheng
wanghaoshuang
dongzhihong
Yang yaming
Yu Yang
zlx
qiaolongfei
dzhwinter
yangyaming
dangqingqing
Yibing Liu
Luo Tao
Liang Zhao
Haonan
helinwang
Helin Wang
liaogang
Peng Li
Zhizhong Su
gaoyuan
Yi Wang
Liu Yiqun
qijun
Haichao-Zhang
emailweixu
zhangruiqing01
zhangjinchao01