e286b950a5
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dilate_conv
8 years ago
74d3ca8bab
Merge branch 'develop' into cross_entropy_over_beam
8 years ago
ab6b3c481a
Merge pull request #3367 from lcy-seso/add_sequence_slice_layer
...
Add a sequence slice layer.
8 years ago
5e59ca7ccc
fix config helper.
8 years ago
e3342ff8e7
Fix android build error.
8 years ago
f715c740bf
Add_config_parser_for_Conv3D_DeConv3D
8 years ago
bc6bae8d53
Merge branch 'develop' into add_sequence_slice_layer
8 years ago
82e4fab4e3
follow comments.
8 years ago
2c8b3c4430
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dilate_conv
8 years ago
d8cd67dd1e
Make cudnn convolution layer and projection support for dilation.
8 years ago
25083de998
Merge branch 'develop' into cross_entropy_over_beam
8 years ago
d7b80f03b0
Correctly handle width and height for some layers
8 years ago
3065cb2625
add huber_regression_cost
8 years ago
7d2ef02a99
Add ScaleShiftLayer
8 years ago
c07cbf7daf
Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-ROIPooling
8 years ago
e6db484d15
make clear that current huber_cost is for two-classification
8 years ago
44ae44da49
add configuratioin helpers.
8 years ago
b7359ee3ce
Merge branch 'develop' into add_sequence_slice_layer
8 years ago
b2bd67133a
rename and refine functions
8 years ago
f6a940936b
remove unused comments, refine and rename
8 years ago
abc49f74af
Merge remote-tracking branch 'upstream/develop' into merge
8 years ago
6373291c77
add test case use_mkldnn_wgt
8 years ago
34ff75221f
Merge branch 'develop' into add_sequence_slice_layer
8 years ago
92b2b1bd73
Merge branch 'develop' into kmax_score_layer
8 years ago
84627bb934
add config helper for sequence slice layer.
8 years ago
83ce2dce5f
split sorting into another layer. fix config helper.
8 years ago
3c3a11a0dc
add use_mkldnn flag
8 years ago
567c1a1f65
add config functions for kmax_sequence_score layer.
8 years ago
6e291b34c3
Merge branch 'develop' into add_nest_sequence_select
8 years ago
b7b956f0ba
Merge branch 'develop' into add-ClipLayer
8 years ago
3fe9e48f36
Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-L2NormLayer
8 years ago
17e16c2548
Refine RowL2NormLayer and add python unit test for it
8 years ago
d3e30146e4
Merge branch 'develop' into add_nest_sequence_select
8 years ago
82911cecb6
Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-ClipLayer
8 years ago
d19355a532
Refine ClipLayer and add unit test for it
8 years ago
dc9f31b32b
Add SliceProjection and slice_projection.
8 years ago
c0ecd5c4c5
add config helper.
8 years ago
23a8d015e0
add ClipLayer
8 years ago
84660653f8
add RowL2NormLayer
8 years ago
ccdc262848
enable v2 use cudnn batch norm automatically.
8 years ago
0f4c733296
add ROIPooling for Fast(er) R-CNN
8 years ago
ec236f4624
fix code format
8 years ago
4d6be9741c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mobilenet_gpu
8 years ago
77ff97ab38
fuse interface of depthwise to expand in python api
8 years ago
a6c53fc2fc
fix python wrapper bugs
8 years ago
60a788933b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer
8 years ago
3e7819c276
1. Reading image shape from input data instead of image_config
...
2. Add crop layer unitest
3. Fix bugs
8 years ago
e8ee07f31f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pixel_softmax_layer
8 years ago
1cdf149b6f
1. delete PixelSoftmaxLayer and add SwitchOrderLayer
...
2. Make SwitchOrderLayer support for softmax activation
3. Fix bugs
8 years ago
d50c71f3e2
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mobilenet_gpu
8 years ago
84a0d6d898
Merge pull request #2572 from skylian/error_clipping
...
Enable error clipping for fc layer
8 years ago
2bc08f8914
modify format accored with clang-format 3.8
8 years ago
0152d97e63
fix pixel softmax python wrapper bug
8 years ago
de5ded6bbd
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer
8 years ago
69b12225cc
fix crop layer python wrapper bug
8 years ago
3aa679814f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pixel_softmax_layer
8 years ago
29f25fbe03
Add pixel softmax layer for FCN model
...
1. Add switch function for switching image dimensions order
2. Add CpuMatrix::backwardSoftmax function
3. Add pixel softmax layer, python wrapper and grad_test
8 years ago
36e7800aa1
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mobilenet_gpu
8 years ago
075954c17c
follow comment.
8 years ago
dc60671127
Merge branch 'develop' into enable_error_clipping_for_fc
8 years ago
203364281e
enable error clipping in FC layer.
8 years ago
d378e0a0cd
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_layer
8 years ago
7f380c1be3
Merge pull request #2701 from luotao1/stride
...
stride pooling for max and average layer
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
211f83fa22
set depthwise conv layer interface in python
8 years ago
0e61730039
stride pooling for max and average layer
8 years ago
0c70f34c60
Fix bug for flowers dataset and row_conv.
8 years ago
b5ab4b69bc
Follow comments, mainly use std::copy to simplify logic.
8 years ago
5e87e27c75
fix error clipping
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
61222578b4
Allow printer layer to print user provided message
...
For example:
layer.printer(input=[x, y], format="x=%s y=%s")
8 years ago
8266546eb2
Merge pull request #2480 from emailweixu/repeat_layer
...
Repeat layer for column vector
8 years ago
65969dad64
Add DetectionOutputLayer and MultiBoxLossLayer.
8 years ago
226f810352
Add activiation for repeat_layer
...
Also remove active_type argument for many layers in config_parser.py because it is automatically
handled by LayerBase.
8 years ago
ef61288f9e
Clean-up recurrent group related python code
...
No longer need to specify target_inlinks or is_seq.
8 years ago
fc0ad9048a
Repeat layer for column vector
8 years ago
17994e38aa
RecurrentGroup with mixed input sequence types
...
No longer need to use SubsequenceInput. The framework will detect.
8 years ago
2207659250
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into ssd_map
8 years ago
6248e566f9
merge from remote
8 years ago
dd2cbb63bf
Parameter initializer in V2 API
...
User can provide an initializer in ParamAttr. The initializer will be called when at parameters.create().
8 years ago
23b1a27483
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
997cef2e63
tiny modify
8 years ago
597a58c3ef
Add DetectionMAPEvaluator.
8 years ago
97a2fde995
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
6bc9277503
Merge branch 'develop' into row_conv
8 years ago
892b1f9ff6
Merge branch 'develop' into fix_config_parsing_bug
8 years ago
37015fadbd
update code
8 years ago
c7483bf956
add configuration helper for prelu layer.
8 years ago
692d251869
add missing configuration functions in v2 API.
8 years ago
18cd1f2558
Fix bug and Python API.
8 years ago
18435f2a73
modify the pruning from reading mask to specify sparsity_ratio
8 years ago
ca55a24eb3
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into improve_pruning
8 years ago
5413af8d11
imporve pruning module
8 years ago
97c4d23fab
Add docs and clean up unused code
8 years ago
7d0355cdd0
Fix V2 API
8 years ago
7430d30598
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into variable_input
8 years ago
2e4c0bd2ea
enable global gradient_clipping_threshold
...
correct a typo
optimize code
fix a bug
8 years ago
576e7f4779
Support variable-dimension for convolution operation.
8 years ago
23e00ba379
follow comments
8 years ago
32ecc191f1
Merge pull request #2100 from Yancey1989/fix2060
...
Bugfix: checkout input_type failed
8 years ago
3c5e0f8a5d
remove g_pass_height_width in config_parse.py
8 years ago
85502783aa
Bugfix: checkout input_type failed
8 years ago
1fd00758ac
SmoothL1 loss
8 years ago
d369577fed
add reversed poolSequenceWithStride
8 years ago
0291c01884
Merge branch 'develop' into stride
8 years ago
5961b52b13
Merge pull request #1653 from Noplz/normalize-layer
...
CrossChannelNorm Layer for SSD
8 years ago
9298a9ec0d
stride pooling for seqlastin and seqfirstin
8 years ago
ec7184ac18
fixed a bug in conv_projection issue #1681
8 years ago
090c974e4b
completed implementation of cudnn_convt convTransProjection and convTransOperator
8 years ago
07c1ea258f
python interface for convTransProjection and convTransOperator
8 years ago
8c2d1bad7a
Merge branch 'develop' into normalize-layer
8 years ago
eb43d93a58
Change Normalize layer to CrossChannelNorm layer
8 years ago
bd4ec1b493
Merge branch 'develop' into memory.set_input
8 years ago
03889bab6f
Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
4375a64ea1
fix bug to pass travis
8 years ago
bf838034d6
Merge branch 'develop' into fix-crf-weight-and-coeff-bug
8 years ago
eea0097dcb
NormalizeLayer for SSD
8 years ago
1d58949a40
Merge branch 'develop' into enable_drop_in_average_and_max_layer
8 years ago
fd41a87a53
complete data_type documentation
8 years ago
e87181db8d
use value_range instead of ele_range
8 years ago
fa3b1c465b
change argument name of data_type.integer_value/integer_value_sequence to ele_range, add documentation.
8 years ago
e768721cd9
fix calculating totalScore2_ bug
8 years ago
7d551dd484
Make it possible to postpone setting the layer name for a memory.
...
The reason for adding the function is exemplified in the following hypothetical code:
mem = memory(name=None, size=256)
hidden = fc_layer(input=mem)
state = hidden + x
mem.set_input(state)
In the above code segment, it would be very annoying if we require the user to provide
the name at memory() call because the layer name of state is automatically generated
and is not easy to set it.
Change-Id: I918bf1d3d5c26addd88a6f7021e98b3e0e9df494
8 years ago
ccb553fec4
Merge pull request #1253 from wangkuiyi/python_learning_and_refactor
...
Rename Python function DataBase into create_data_config_proto
8 years ago
b8f3a5c433
Correct the wrong deletion of a single character
8 years ago
b36df98d01
Correct Python identation
8 years ago
058eeac0fc
Revert "Remove completely create_data_config_proto"
...
This reverts commit ab279beed1
8 years ago
ab279beed1
Remove completely create_data_config_proto
8 years ago
996b1de1d8
Rename DataBase into create_data_config_proto
8 years ago
6245fed240
rotate_layer python interface fixes
8 years ago
55eb2fcffa
format correction
8 years ago
781b85b5fc
rotate_layer and flip_layer * added getMin and getMax for GpuMatrix * gru_step_layer parameter name
8 years ago
04b5daf92d
change the parameter position of gru_step_layer from 1 back to 0
8 years ago
6da7283475
make gru_group parameters sharable
8 years ago
8d47499e1d
update code
8 years ago
19cb2a7fb3
fix default value of cos_sim scale
8 years ago
6b61a096e1
Optional padding mode, namely ceil or floor, ceil by default.
8 years ago
8b5431d5e1
padding operation
8 years ago
cbbad4202a
delete the modification of SlopeInterceptLayer.
8 years ago
08a817e3fb
delete unnecessary parameters and modifications for some mathmatical
...
layers.
8 years ago
ce939b30ba
enable dropout rate in several computation layers.
8 years ago
15a6252f8e
Merge branch 'develop' into enable_drop_in_average_and_max_layer
8 years ago
e022c065d7
enable dropout in average and max layer.
8 years ago
843b63bb84
add config_parser in trainer_config_helpers to seperate trainer config
8 years ago
c6d9d04004
Merge pull request #979 from reyoung/feature/fix_param_hidden_in_pydp2
...
A tiny fix in PyDataProvider2
8 years ago
16ea66e8ed
Merge branch 'develop' of github.com:baidu/Paddle into feature/mnist_train_api
8 years ago
e031f0c4e8
Fix typo in PyDataProvider2.py
8 years ago
wanghaoshuang
caoying03
Cao Ying
chengduoZH
xuwei06
Luo Tao
guosheng
tensor-tang
Guo Sheng
hedaoyuan
xzl
emailweixu
Yang yaming
dangqingqing
lianxiaochen
yangyaming
Yibing Liu
Yancey
wangyang59
Yuan Gao
gaoyuan
Yu Yang
Peng Li
Helin Wang
Liang Zhao
wangkuiyi
Yi Wang
王益
Haonan
zhangruiqing01
qiaolongfei
hedaoyuan