Yibing Liu
dc186af729
Merge branch 'develop' of upstream into margin_rank_loss_op_dev
8 years ago
Yibing Liu
367a54e08c
Merge pull request #4360 from kuke/multiplex_modify_dev
...
Modify multiplex_op
8 years ago
chengduoZH
30a586df0c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into Add_pool_op
8 years ago
caoying03
3d77360b89
add negative clipping for softmax.
8 years ago
caoying03
360bde9a70
Merge branch 'develop' into softmax_with_cross_entropy_op
8 years ago
Cao Ying
7d65321620
Merge pull request #4237 from lcy-seso/optimize_cross_entropy_kernel
...
optimize cross entropy kernel.
8 years ago
caoying03
000d75116f
fix backward op.
8 years ago
Yibing Liu
089f8e2d37
Merge branch 'develop' of upstream into multiplex_modify_dev
8 years ago
caoying03
8b8ad6b164
fix implementations of supporting soft labels.
8 years ago
fengjiayi
6915c924a4
Fix bug
8 years ago
fengjiayi
4fb106afb0
Merge branch 'feature/pybind_for_protobuf_desc' of https://github.com/reyoung/Paddle into feature/pybind_for_protobuf_desc
8 years ago
fengjiayi
5419f16b38
Add unittests
8 years ago
Yu Yang
16c5f629bd
Complete unittest for OP
8 years ago
Yu Yang
f9f910a33b
Complete op
8 years ago
Yu Yang
1cd2014007
Merge branch 'develop' of github.com:baidu/Paddle into feature/pybind_for_protobuf_desc
8 years ago
Zhuoyuan
e5a3c1d2d5
Merge pull request #4372 from reyoung/feature/stable_prelu_grad_test
...
Stabilize prelu gradient check
8 years ago
Zhuoyuan
f698a49ce3
Merge pull request #4240 from zchen0211/develop
...
lstm unit
8 years ago
Yu Yang
d54e8420be
Stabilize prelu gradient check
8 years ago
Yibing Liu
236af56612
separate index tensor from candidate tensors in multiplex_op
8 years ago
chengduoZH
b72854389e
Fix (According to the review)
8 years ago
Liu Yiqun
9f32c8d896
Merge branch 'develop' into core_add_sequence_softmax_op
8 years ago
Yibing Liu
47fbc96fa1
Merge pull request #4064 from kuke/multiplex_op_dev
...
Add multiplex operator
8 years ago
Tao Luo
01bec25734
Merge pull request #4193 from luotao1/seq_pool
...
implement framework of seq_pool_op and its unitest
8 years ago
caoying03
bb58b63b6c
Merge branch 'develop' into softmax_with_cross_entropy_op
8 years ago
guosheng
1295e5ef54
Refine reduce_op unit test and add newline at end of file
8 years ago
guosheng
c8d877195b
Revise the reduce_op unit test accordingly
8 years ago
guosheng
3994e91a67
Add reduce_op
8 years ago
caoying03
201c2bcf20
delete redundant codes.
8 years ago
caoying03
6735585b0f
fix cpu kernel with soft labels.
8 years ago
Yu Yang
9fa7c9306c
Merge branch 'feature/pybind_for_protobuf_desc' of github.com:reyoung/Paddle into feature/pybind_for_protobuf_desc
8 years ago
fengjiayi
08e9900621
Fix bugs
8 years ago
Yu Yang
b941865d44
Merge branch 'feature/simplify_attr_parse' into feature/pybind_for_protobuf_desc
8 years ago
fengjiayi
57c95c7957
Merge branch 'fix_lod_tensor_dim_64' into feature/pybind_for_protobuf_desc
8 years ago
Yu Yang
ddf2448484
Update Input/Output of Op
8 years ago
Yu Yang
dc643a3352
Hot fix unittest
8 years ago
Yu Yang
bddb40609d
Buggy code
8 years ago
fengjiayi
f5aa8b4d7e
Update namespace of pybind/protobuf.cc and .h
8 years ago
fengjiayi
6db6475460
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/pybind_for_protobuf_desc
8 years ago
fengjiayi
ee547f6ac9
Add unittests
8 years ago
superjom
b545b5b86b
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into feature/recurrent_op_backward_fix
8 years ago
caoying03
30bfaab36e
Merge branch 'develop' into optimize_cross_entropy_kernel
8 years ago
gongweibao
f99841dd2a
Elementwise operator. ( #4139 )
...
Elementwise operator add/sub/mul/div
8 years ago
dangqingqing
efb56db770
tune max_relative_error in test_cos_sim_op.
8 years ago
qingqing01
7831b1d9ea
Merge branch 'develop' into attr_bool
8 years ago
chengduoZH
c2c2d610a4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into Add_pool_op
8 years ago
Yu Yang
618884dd69
Complete unittest for ProgramDesc
8 years ago
Yu Yang
70f398e207
Update
8 years ago
dangqingqing
0dce16a697
Use bool type for attr in cross_entropy_op.
8 years ago
Yibing Liu
85a5d38446
Merge branch 'develop' of upstream into multiplex_op_dev
8 years ago
chengduoZH
6f61b5df7d
fix unit test
8 years ago
Luo Tao
0449b9c89e
Merge branch 'develop' into seq_pool
8 years ago
chengduoZH
84a2512b90
fix parameter name and function define
8 years ago
Yibing Liu
756af4e73a
regulate comments in margin_rank_loss_op
8 years ago
dangqingqing
58e3ad0a70
Fix conflicts.
8 years ago
caoying03
f1d5fb3b9a
support soft labels.
8 years ago
Yibing Liu
6b3e9ccb3a
pass unit test for margin_rank_loss_op
8 years ago
chengduoZH
50b8ec0564
fix unit test
8 years ago
Yibing Liu
2f12256186
Merge branch 'develop' of upstream into margin_rank_loss_op_dev
8 years ago
dangqingqing
6e2782e958
update to develop branch.
8 years ago
caoying03
a2a0d6f82a
Merge branch 'develop' into softmax_with_cross_entropy_op
8 years ago
chengduoZH
3416f5e0f8
fix function define
8 years ago
Liu Yiqun
4d9293940b
Merge branch 'develop' into core_add_sequence_softmax_op
8 years ago
chengduoZH
510f00800a
Add pool3d unit test
8 years ago
chengduoZH
33d9999890
Add pool2d unit test
8 years ago
hedaoyuan
0ee967b513
Merge pull request #4288 from hedaoyuan/fix_bug
...
Bug fix for get device_context in conv2d op.
8 years ago
hedaoyuan
ccbb285311
Increase the max_relative_error in TestConv2dOp.
8 years ago
QI JUN
8c3b8af31e
Merge pull request #4071 from QiJune/activation_ops
...
Implement activation related operators
8 years ago
Yibing Liu
d827359c71
Merge pull request #4098 from kuke/rank_loss_op_dev
...
Add rank loss operator
8 years ago
whs
da2aabb628
Merge pull request #3906 from wanghaoshuang/crop_op
...
Add crop op
8 years ago
superjom
27aaee1181
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into feature/recurrent_op_backward_fix
8 years ago
Yibing Liu
cf4b2db758
change the dims of input of rank_loss_op
8 years ago
Yibing Liu
79c2d90a7f
add margin_rank_loss_op
8 years ago
Liu Yiqun
f14a7966b0
Initialize the sequence softmax operator.
8 years ago
whs
e53dc8a2e4
Merge pull request #3937 from wanghaoshuang/clip_op
...
Add clip op
8 years ago
X.Dragon
c003895c1c
Merge pull request #3920 from NHZlX/op_transpose
...
add the transpose op
8 years ago
superjom
0da8133224
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into feature/recurrent_op_backward_fix
8 years ago
superjom
6a0c342874
make RecurrentOp's backward work
8 years ago
hedaoyuan
7a891a3321
Merge pull request #4042 from hedaoyuan/conv_op
...
Convolution operator
8 years ago
Yan Chunwei
b5e67fce70
RNNOp remove alias ( #4274 )
...
* remove alias
8 years ago
wanghaoshuang
bc632df822
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
8 years ago
wanghaoshuang
c7b6d2c46d
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into clip_op
8 years ago
superjom
68399ab921
Merge remote-tracking branch 'origin/rnn-backward-python' into feature/recurrent_op_backward_fix
8 years ago
Zhuoyuan
40e49c3f8b
update python test
8 years ago
superjom
075e0e3c5d
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into rnn_remove_alias
8 years ago
superjom
3c29224ef3
remove alias
8 years ago
zchen0211
7883227716
lstm
8 years ago
caoying03
a3a8a0900d
optimize cross entropy kernel by using reduce.
8 years ago
Yibing Liu
9da5192f77
adapt multiplex_op to the dev of framework
8 years ago
Yang yaming
51f1148921
Merge pull request #3987 from pkuyym/fix-3923-c
...
Add modified huber loss operator
8 years ago
Yibing Liu
18dc201bd9
merge multiplex_op with the latest upstream
8 years ago
dangqingqing
39cf2e217d
update to develop branch.
8 years ago
dangqingqing
b65709e403
Share LoD between input and output of each opeators.
8 years ago
Yibing Liu
ece329100a
refine rank_loss_op
8 years ago
yangyaming
308ce9ac55
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3923-c
8 years ago
yangyaming
4e3ba65f19
Refine doc.
8 years ago
yangyaming
12596a16ec
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3789
8 years ago
xzl
1792e58f20
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into op_transpose
8 years ago
xzl
0cd9b8c0aa
modify the input\output name to X\Out
8 years ago
Yibing Liu
f2cfa32411
Merge branch 'develop' of upstream into rank_loss_op_dev
8 years ago
wanghaoshuang
3f3848cdf7
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into clip_op
8 years ago
dangqingqing
72ba02701b
Add bool type for attribute and use it in dropout_op.
8 years ago
superjom
b818e64720
Merge branch 'develop' of github.com:PaddlePaddle/Paddle into rnn_remove_alias
8 years ago
superjom
0d7e4294fc
remove alias
8 years ago
dangqingqing
7ee916b0d3
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into attr_bool
8 years ago
dangqingqing
2aa4d326ec
Fix unit testint in test_prelu_op.
8 years ago
wanghaoshuang
a3c3b7866e
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into clip_op
8 years ago
wanghaoshuang
ce709b75b3
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
8 years ago
typhoonzero
12f0a86f36
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into auc_op
8 years ago
qingqing01
5b42d2b21b
Merge pull request #4081 from xinghai-sun/soft_label_cross_entropy
...
Add soft-label support for cross-entropy operator.
8 years ago
Tao Luo
de8aaf6c00
Merge pull request #4192 from qingqing01/fix_prelu
...
Fix compile error in prelu_op.
8 years ago
qingqing01
5882c1f6f0
Remove test_prelu_op since it failed and will be fixed later.
8 years ago
Xinghai Sun
19de8ae141
Fixed a error in mnist unitest.
8 years ago
Luo Tao
1b01f1ea7b
implement framework of seq_pool_op and its unitest
8 years ago
Xinghai Sun
d8046da0cd
Use soft_label attribute for cross-entropy.
8 years ago
Xinghai Sun
c7f91a94ec
Merge pull request #3817 from xinghai-sun/dropout
...
Add dropout operator.
8 years ago
wanghaoshuang
a4b1abe5c4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
8 years ago
dangqingqing
fad48fa6b1
Add bool type for attr.
8 years ago
Xinghai Sun
8e7fe8cae5
Merge branch 'develop' into soft_label_cross_entropy
8 years ago
Xinghai Sun
ffeeef82f3
Remove unnecessary mask operations in test phase for dropout operator.
8 years ago
Zhuoyuan
f86c1ccdbe
Merge pull request #4121 from zchen0211/develop
...
Prelu with forward, backward and python test passed
8 years ago
wanghaoshuang
fa4908dc10
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
8 years ago
xzl
a9a7ba3cff
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into op_transpose
8 years ago
xzl
9de45e113a
fixed bug when dims.size == 1, modify the variable naming, add judgement when input_grad is null
8 years ago
Xinghai Sun
a2798ff25f
Merge branch 'develop' into dropout
8 years ago
zchen0211
154d88c261
fix gradient not stable
8 years ago
zchen0211
3c3a6d90ae
prelu finalize
8 years ago
zchen0211
4a2378845e
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
Xinghai Sun
585d12a307
Add is_training attr and testing phrase compuation to dropout operator.
...
Change type of dropout_prob to template typename.
8 years ago
hedaoyuan
f3669ca3f1
Support input_grad = null or filter_grad = null.
8 years ago
xzl
35967e8658
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into op_transpose
8 years ago
xzl
5ede6fd434
delete cuda impl, complete comments, modify variable naming
8 years ago
Liu Yiqun
466d48fd23
Check and only check the output varibles specified by self.outputs.
8 years ago
Yancey
56b1b70142
Split operator with CPU kernel ( #4046 )
...
Split Op CPU Kernel
8 years ago
wanghaoshuang
8d9d537b9f
remove op_test_util.py
8 years ago
wanghaoshuang
44224f4b5b
remove gradient_checker.py
8 years ago
wanghaoshuang
3102a52a67
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into clip_op
8 years ago
wanghaoshuang
a345b7195e
1. Add CUDA stream when launching kernel.
...
2. Fix unitest.
3. Fix comments and some issues.
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into clip_op
8 years ago
Yiqun Liu
ec9a55aea4
Merge pull request #3927 from Xreki/core_add_fc_op
...
Port fully connected operator
8 years ago
武毅
8580dce308
Refine accuracy_op CUDA kernel ( #4097 )
...
* refind accuracy_op
* follow comments
* follow comments
8 years ago
wanghaoshuang
57a3b8b69e
1. Implement GPUCrop kernel instead of eigen.
...
2. Fix unitest
8 years ago
Yibing Liu
26b393f911
Merge branch 'develop' of upstream into rank_loss_op_dev
8 years ago
hedaoyuan
5a4138b66b
Add test with groups=1.
8 years ago
qijun
87ba6cbf20
merge baidu/develop
8 years ago
wanghaoshuang
2321a37b3c
fix issues
8 years ago
caoying03
8f8ea005fe
fix implementations.
8 years ago
hedaoyuan
7bf1e76fdc
Merge branch 'develop' of https://github.com/baidu/Paddle into conv_op
8 years ago
Xinghai Sun
0532662902
Merge branch 'develop' into dropout
8 years ago
Xinghai Sun
e87068290e
Update cross entropy operator by following reviewer's comments.
8 years ago
Xinghai Sun
d7717f2e6b
Merge branch 'develop' into soft_label_cross_entropy
8 years ago
zchen0211
1b2374ad3b
new prelu with functor
8 years ago
zchen0211
384368f42c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
wanghaoshuang
57011b2022
reste
8 years ago
wanghaoshuang
e2d75bd364
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
8 years ago
wanghaoshuang
b21aee635e
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
...
Conflicts:
paddle/pybind/pybind.cc
8 years ago
dangqingqing
05680d0d5a
Add unit testing for sequence average pool operator.
8 years ago
dangqingqing
90886443b4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into seq_op_test
8 years ago
dangqingqing
d6a0280eb9
Enhance unit testing framework for operator with LoDTensor.
8 years ago
wanghaoshuang
a8584a9902
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
...
Conflicts:
paddle/pybind/pybind.cc
8 years ago
Liu Yiqun
6ce4bf3645
Merge branch 'develop' into core_add_fc_op
8 years ago
yangyaming
3ee87653b4
Tight the relative error.
8 years ago
Liu Yiqun
eef1ccbf08
Add the check of inputs and outputs in all operators.
8 years ago
caoying03
1fb5f12f0c
Merge branch 'develop' into softmax_with_cross_entropy_op
8 years ago
caoying03
efa4526c52
finish implementation and fix unittest.
8 years ago
zchen0211
490ca5f1ae
prelu_op
8 years ago
qijun
fd559b3a7e
Merge remote-tracking branch 'baidu/develop' into activation_ops
8 years ago
qijun
48f5f6bdd0
refine some operators' python unittests
8 years ago
zchen0211
260026fa67
prelu modify
8 years ago
zchen0211
58b5b08bba
prelu op
8 years ago
zchen0211
299dcb6715
merge with new change
8 years ago
xzl
6b3ae01e02
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into op_transpose
8 years ago
yangyaming
09a13f6c49
Using LoDTensor and adapt to new unittest.
...
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3789
8 years ago
Liu Yiqun
cb7d718611
Merge branch 'develop' into core_add_fc_op
8 years ago
qijun
fd5aa2ada2
merge baidu/develop
8 years ago
Yibing Liu
f2442be9e3
merge conflicts
8 years ago
qijun
5824d85001
add activation operators and python unittests
8 years ago
dangqingqing
48000a8f2d
Update to develop branch and resovle conflicts.
8 years ago
Cao Ying
0e46f5ebd7
Merge pull request #4094 from lcy-seso/fix_cross_entropy_op_output_shape
...
fix shape of output tensor of cross_entropy_op.
8 years ago
Yibing Liu
36f349e71e
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rank_loss_op_dev
8 years ago
Liu Yiqun
989e8358b3
Reuse the output of mul when there is only one input in FCOp.
8 years ago
whs
012db97241
Merge pull request #4103 from wanghaoshuang/pad_op
...
Fix unitest of pad_op
8 years ago
Liu Yiqun
fe2ab2ee7f
Set the default value of xNumColDims and rename the output to "Out" in FCOp.
8 years ago
wanghaoshuang
481a8370ac
update unitest
8 years ago
Xinghai Sun
c5972faca9
Merge pull request #3918 from xinghai-sun/cos_sim_vector
...
Add broadcasting support (e.g. matrix-vector) for cos sim operator.
8 years ago
wanghaoshuang
680da5c9d0
Fix unitest of pad_op
8 years ago
Yibing Liu
7c423e4b0d
add unit test for rank_loss_op
8 years ago
Liu Yiqun
0b21b854ec
Make the weights of FCOp a fixed 2-D matrix and refine some comments in FCOp.
8 years ago
wanghaoshuang
b299d07fbe
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
...
Conflicts:
paddle/pybind/pybind.cc
python/paddle/v2/framework/tests/op_test_util.py
8 years ago
caoying03
e0ca4d7a29
fix shape of output tensor of cross_entropy_op.
8 years ago
武毅
2d6233646a
Accuracy op ( #3907 )
...
* init add
* add topk op
* someupdate
* fix style check
* add test py file
* update top k cuda kernel
* follow comments
* remove debug print
* accuracy_op
* fix casting error
* fix casting error
* fix casting error
* fix rename bug...
* make it smaller
* update cast
8 years ago
qijun
3110bf9a9a
merge activation operator python tests
8 years ago
zchen0211
f6dee08d76
new changes
8 years ago
zchen0211
c7db6e8d14
cond op passed
8 years ago
wanghaoshuang
7deddab1ff
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
...
Conflicts:
paddle/pybind/pybind.cc
8 years ago
dangqingqing
30a58b5121
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into lod_tensor2
8 years ago
dangqingqing
f299206396
Using LoDTensor instead of Tensor in every operator.
8 years ago
Xinghai Sun
6d60352e7e
Add soft-label support for cross-entropy operator.
8 years ago
whs
08f9b72dbf
Merge pull request #3765 from wanghaoshuang/pad_op
...
Add pad op
8 years ago
yangyaming
ce15d89afa
Adapt to new unittest.
8 years ago
yangyaming
df83ac4c7b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3923-r
8 years ago
yangyaming
6d4c440576
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3923-c
8 years ago
Liu Yiqun
af2eb94909
Support inputs and weights of multi-dimensions and refine the output names.
8 years ago
Yancey
47975870aa
Fix check grad with multioutput ( #4067 )
...
Fix check grad with multi outputs
8 years ago
Liu Yiqun
8495f3f04a
Merge branch 'develop' into core_add_fc_op
8 years ago
yangyaming
ec92588a37
Fix some conflicts and correct unittest.
...
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3923-c
8 years ago
qijun
4e173527c1
fix op python tests
8 years ago
qijun
b50a507617
add activation operator python test
8 years ago
qijun
d736fc0e00
add activation macro
8 years ago
Yibing Liu
4a71d954e9
merge conflicts
8 years ago
Yibing Liu
b3f44ad761
add multiplex operator
8 years ago
hedaoyuan
b4ba35caeb
Add groups test.
8 years ago
Xinghai Sun
965fd2250d
Merge branch 'develop' into cos_sim_vector
8 years ago
typhoonzero
c7eef34c28
auc cpu only
8 years ago
caoying03
8d88c52d8a
Merge branch 'develop' into softmax_with_cross_entropy_op
8 years ago
caoying03
c6366c819e
softmax as functor.
8 years ago
gongweibao
8778957cfc
Add element-wise multiplication operator. ( #3787 )
...
Add element-wise multiplication operator
8 years ago
dangqingqing
d11430e009
Use the inheritance in the definition of LoDTensor.
8 years ago
wanghaoshuang
23381dd16a
Update pad op unitest
8 years ago
hedaoyuan
14ae805014
Merge branch 'develop' of https://github.com/baidu/Paddle into conv_op
8 years ago
wanghaoshuang
d89598054e
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pad_op
8 years ago
zchen0211
b8e75c1f1a
cond op
8 years ago
hedaoyuan
a7c1872206
Refine test_conv2d_op.py
8 years ago
hedaoyuan
c671189d7f
Fix test_conv2d_op.py.
8 years ago
hedaoyuan
3705de6ddd
Merge branch 'develop' of https://github.com/baidu/Paddle into conv_op
8 years ago
Luo Tao
8a2ff350ed
simplify the python/paddle/v2/framework/tests/CMakeLists.txt
8 years ago
hedaoyuan
40fe0a8c47
Add backward of convolution.
8 years ago
caoying03
2507bcaa29
Merge branch 'develop' into softmax_with_cost_op
8 years ago
Yibing Liu
4137cb0baf
Merge pull request #3949 from kuke/reshape_op_dev
...
Add reshape operator
8 years ago
Yibing Liu
dd926498e7
adapt to the new test framework
8 years ago
qingqing01
6d0d29f645
Merge pull request #4001 from qingqing01/lod_tensor_py
...
Correctly use host_vector in LoDTensor and expose LoDTensor to Python.
8 years ago
Yibing Liu
31cbb3432f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into reshape_op_dev
8 years ago
wanghaoshuang
a03c6849e7
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pad_op
8 years ago
qijun
a3ec652110
fix bug
8 years ago
hedaoyuan
c9d8cb4e90
Convolution op and forward calculation.
8 years ago
qijun
d6c3794cff
merge baidu/develop and remove unused gradient_checker/op_test_util
8 years ago
Liu Yiqun
4f2ee63c44
Get rid of the calling of inplace op in FCOp.
8 years ago
dangqingqing
28dc434036
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into lod_tensor_py
8 years ago
dangqingqing
68943f59aa
Add construction function for LoDTensor in pybind.
8 years ago
qijun
477b23c3f5
follow comments
8 years ago
qijun
436fbb0d6a
Merge remote-tracking branch 'baidu/develop' into refine_op_test
8 years ago
Yancey1989
76a70d10db
fix unit test error
8 years ago
qijun
9d46f443fe
fix attr bug in op_test and ensure order in duplicate inputs/outputs
8 years ago
Yibing Liu
7ae72f752d
remove unused code in test
8 years ago
qijun
2d807f2b4c
init refine op python tests
8 years ago
Yancey
7bd517129a
Add Concat operator with CPU kernel ( #3775 )
...
add concat op with CPU kernel
8 years ago
Yibing Liu
477d92bcd2
merge conflicts
8 years ago
Yibing Liu
dd64349a92
refine reshape operator
8 years ago
Liu Yiqun
4223ff8c27
Correct the key name of "mul" op in FCOp, and add some annotations for debug.
8 years ago
Liu Yiqun
70e60d73f9
Merge branch 'develop' into core_add_fc_op
8 years ago
xzl
e129dcfb74
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into op_transpose
8 years ago
Liu Yiqun
d874fca46b
Support multiple inputs in FCOp.
8 years ago
dangqingqing
372ede1527
update and fix conflicts.
8 years ago
dangqingqing
d0dbc0610f
Correctly use host_vector in LoDTensor and expose LoDTensor to Python.
8 years ago
wanghaoshuang
e1da6c06c2
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pad_op
8 years ago
QI JUN
c1696696a3
Merge pull request #3882 from QiJune/refactor_op_py_test
...
Refactor operator python test framework and add sum operator
8 years ago
Yibing Liu
02da0d1bb2
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into reshape_op_dev
8 years ago
yangyaming
1c81d57938
Add huber loss operator.
8 years ago
yangyaming
984117458c
Finish modified huber loss op.
8 years ago
xzl
4da89f28cb
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into op_transpose
8 years ago
xzl
828008e41d
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into op_transpose
8 years ago
xzl
d6651b9b8e
fixed bug of the gpu impl
8 years ago
qingqing01
4c68405c95
Fix name in test_lookup_table
8 years ago
yangyaming
3a49bae0b4
Finish forward for GPU and CPU and CPU backward.
8 years ago
wanghaoshuang
d79e3e4d9b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pad_op
8 years ago
wanghaoshuang
0910a9bac4
Refine pad op
...
1. Rename variables by Google style.
2. Add more test cases.
3. Add more detail and meaningful comments.
4. Change type of "padding" to vector<int>
8 years ago
qijun
c0192889cc
fix code style
8 years ago
qijun
15627e48d8
fix gou test bug
8 years ago
caoying03
2070bc936d
Merge branch 'develop' into softmax_with_cost_op
8 years ago
qijun
090b8114e6
merge baidu/develop
8 years ago
qijun
f50e36e285
follow comments
8 years ago
fengjiayi
f6e72c93c7
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dev_add_axis
8 years ago
武毅
3fbb692d4b
Add topk op ( #3760 )
...
* init add
* add topk op
* someupdate
* fix style check
* add test py file
* update top k cuda kernel
* follow comments
* remove debug print
* fix casting error
* fix casting error
* fix casting error
* fix rename bug...
* fix travis
8 years ago
Yibing Liu
899c7d6b35
pass unit test
8 years ago
Liu Yiqun
c05d319c2d
Merge branch 'develop' into core_add_fc_op
8 years ago
Liu Yiqun
734a9eeaa4
Correct the definition of Operator in TestFCGradOp, and rename the output name
...
of identity to Y.
8 years ago
Cao Ying
da66891b94
Merge pull request #3928 from lcy-seso/refine_softmax_op
...
Refine names and doc of some operators.
8 years ago
caoying03
5b4526fabc
rename input and output of softmax_op.
8 years ago
Yibing Liu
12eaa22ad2
add reshape operator
8 years ago
yangyaming
0728943d0c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3789
8 years ago
fengjiayi
b7444306ba
Follow comments
8 years ago
caoying03
e61485e0f7
Merge branch 'develop' into refine_softmax_op
8 years ago
wanghaoshuang
320df7ade4
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into clip_op
8 years ago
wanghaoshuang
987cdf1168
Add clip op
8 years ago
fengjiayi
823bdd670f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dev_add_axis
8 years ago
fengjiayi
f2a66ffabb
Follow comments
8 years ago
Xinghai Sun
963a4f3c4e
Update by following reviewers' comments.
...
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dropout.
8 years ago
Liu Yiqun
3285b00df5
Merge branch 'develop' into core_add_fc_op
8 years ago
caoying03
7d16fe87a3
refine softmax operator.
8 years ago
Liu Yiqun
1348c20e2f
Merge branch 'develop' into core_add_fc_op
8 years ago
yangyaming
9802c42555
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3736
8 years ago
Xinghai Sun
16fddf32a5
Add broadcasting support (e.g. matrix-vector) for cos sim operator.
8 years ago
yangyaming
2763f3e32f
Complete smooth_l1_loss_op.
8 years ago
wanghaoshuang
96a7c70a7c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into crop_op
8 years ago
wanghaoshuang
06b42e9ec5
Add crop op.
8 years ago
Luo Tao
8ef17ea68f
Merge branch 'develop' into op_refine, fix conflict
8 years ago
Xinghai Sun
b59f301840
Merge pull request #3815 from xinghai-sun/cos_sim_layer2
...
Add cosine similarity operator.
8 years ago
caoying03
3e13b9122f
add softmax_with_cost_op.
8 years ago
Liu Yiqun
f196ad0210
Port fully connected operator, the FCOp c++ implementation and python unittest.
8 years ago
Xinghai Sun
a5f1e6d6bd
Update cos_sim operator by following reviewer's comments.
8 years ago
wanghaoshuang
9f8e498138
Fix some issues.
8 years ago
fengjiayi
256d6a33d5
Add axis for rowwise_add_op
8 years ago
wanghaoshuang
6684b55bfc
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pad_op
...
Conflicts:
paddle/operators/CMakeLists.txt
paddle/pybind/CMakeLists.txt
8 years ago
wanghaoshuang
3eadb42d3d
Fix eigen error.
8 years ago
whs
7002e69be2
Merge pull request #3878 from wanghaoshuang/fix_attr
...
Make attribute support for std::vector<std::pair<int, int>>
8 years ago
fengjiayi
e168fc4432
Add unit tests for cases that `mul_op` takes tensors as inputs
8 years ago
Yu Yang
b64aac542a
Merge pull request #3857 from qingqing01/grad_test_for_multi_inputs
...
Enhance the unit test framework to explicitly test whether the operator correctly handles gradients for multiple inputs.
8 years ago
qijun
a22606ca0c
fix bug
8 years ago
qijun
f314330c23
refactor operator python test and add sum operator
8 years ago
wanghaoshuang
e687f3f540
Make attribute support for std::vector<std::pair<int, int>>
8 years ago
Luo Tao
020e45f715
follow comments to revert add_two_op to add_op
8 years ago
dangqingqing
ab55d7933b
revert scatter_op and other mirror changes.
8 years ago
Yu Yang
3d9d32a1c1
Invoke check_grad many times for no_grad_set
8 years ago
dangqingqing
447033296d
Make some operator correctly handle gradients for multi inputs.
8 years ago
Luo Tao
5b93ac7778
package a new USE_NO_KERNEL_OP for USE_OP_ITSELF
8 years ago
Xinghai Sun
c657537b4f
Correct some typos.
8 years ago
Xinghai Sun
b1a185524f
Fixed SEGFAULT of dropout operator in GPU.
8 years ago
Xinghai Sun
91215bcef9
Fix a bug causing wrong gradient results in cos_sim op.
8 years ago
yangyaming
c33ddc74c1
Fix some bugs, add more unittests.
8 years ago
Xinghai Sun
ed72af48ce
Add cos_sim op.
8 years ago
yangyaming
e9cc32820d
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-3736
8 years ago
yangyaming
6bef079660
Follow coding style and move reshaping operation to paddle tensor.
8 years ago
yangyaming
a4df3f5bd8
Finish framework of squared_l2_distance_op.
8 years ago
wanghaoshuang
2db7dedea9
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pad_op
...
Conflicts:
paddle/pybind/pybind.cc
8 years ago
wanghaoshuang
26cec83901
Add pad op
8 years ago
qingqing01
751d8533e8
follow wuyi's comments.
8 years ago
qingqing01
c19eae4c8e
update doc about how to write new operators.
8 years ago
qiaolongfei
787cb8ce5d
reset pass num to 1
8 years ago
qiaolongfei
721b5020fa
change predict size to label class_num
8 years ago
zchen0211
bfeecfd3d2
fix problems
8 years ago
zchen0211
97649bf9b2
fix codes in scatter
8 years ago
zchen0211
2edb69a789
with in-place option
8 years ago
zchen0211
c5e28dd1a0
scatter check in
8 years ago
zchen0211
a88901109b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
qingqing01
3663bd881d
Merge pull request #3620 from qingqing01/lookup_table
...
Add a lookup table op and a CUDA helper.
8 years ago
Qiao Longfei
b9a4b2ee52
Merge pull request #3564 from jacquesqiao/mnist
...
init mnist
8 years ago
qiaolongfei
625b15355a
optimize code
8 years ago
qiaolongfei
3648165b63
add gpu support
8 years ago
qingqing01
aafeff0fde
Merge branch 'develop' into lookup_table
8 years ago
zchen0211
fabfe17a42
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
qiaolongfei
0e300f9bf0
use init_net and random_op to initialize parameter
8 years ago
zchen0211
161a15f055
gradient check
8 years ago
qiaolongfei
37cd8165b3
change 128 to BATCH_SIZE
8 years ago
qiaolongfei
1e4566cac0
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mnist
8 years ago
qiaolongfei
9db4ad6130
reduce pass num to 1
8 years ago
qiaolongfei
cf515e4a72
optimize code and name
8 years ago
qiaolongfei
76677f2577
add test
8 years ago
dangqingqing
068ddcaf92
Resovle conflicts.
8 years ago
qingqing01
fe480b9ebe
Merge branch 'develop' into lookup_table
8 years ago
Yu Yang
25e6c014a4
Merge branch 'feature/identity_op' into feature/minus_op
8 years ago
Yu Yang
b53f4e0be7
Merge branch 'develop' of github.com:baidu/Paddle into feature/identity_op
8 years ago
qiaolongfei
6f4b968f56
can train the parameters
8 years ago
dangqingqing
d8ea560eb2
resolve conflicts
8 years ago
dangqingqing
f188e22b33
Remove set functor and add comapre_grad test
8 years ago
qiaolongfei
a13798e8f7
rename add_op to append_op
8 years ago
qiaolongfei
d41a551693
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mnist
8 years ago
qiaolongfei
d3c65a64dc
fix data reader
8 years ago
qiaolongfei
51792022c9
refine code and add debug info
8 years ago
zchen0211
0a0f194836
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
dangqingqing
a8d072c769
fix bug.
8 years ago
dangqingqing
31f59d2b31
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into lookup_table
8 years ago
qingqing01
f931140663
Merge pull request #3501 from qingqing01/cross_entropy
...
Implement GPU kernel for cross entropy operator.
8 years ago
dangqingqing
1795e57671
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into lookup_table
8 years ago
dangqingqing
0f3b9e4112
lookup table op, cuda helper and set functor
...
1. finish lookup table CPU and GPU kernel
2. Add some cuda helper
3. Add some math funtor
8 years ago
qiaolongfei
5a8fbb7d19
add data
8 years ago
Yu Yang
ce723af062
Merge pull request #3585 from reyoung/feature/rename_to_append_op
...
Rename `Net::AddOp` to `Net::AppendOp`
8 years ago
QI JUN
7443b2e481
Merge pull request #3596 from QiJune/implement_random_function
...
refine random related operators
8 years ago
qijun
36e8e72566
expose random seed to users
8 years ago
zchen0211
53e71b44f4
gather op bp passed
8 years ago
zchen0211
f3df105455
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
qiaolongfei
118dd1494f
can run, for debug
8 years ago
qiaolongfei
f6dd787692
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mnist
8 years ago
zchen0211
d3c29e9d16
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
qiaolongfei
950dbde56c
fix rowwise add grad op
8 years ago
Yu Yang
d3f219aa99
Change IdentityOp to ScaleOp
8 years ago
Yu Yang
c108d6108c
Identity operator and its gradient
8 years ago
qijun
d525abed95
refine random related ops
8 years ago
Yu Yang
f1e5533541
Rename `Net::AddOp` to `Net::AppendOp`
...
Fix #3582
8 years ago
dangqingqing
a8863a8d5b
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into cross_entropy
8 years ago
dangqingqing
8f6c8780a5
Replace functor by function.
8 years ago
qiaolongfei
137537b14f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mnist
8 years ago
zchen0211
78553768ba
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop
8 years ago
dongzhihong
b59002daef
"fix math gemm lda order error"
8 years ago
dongzhihong
2799da6634
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mul_op
8 years ago
Qiao Longfei
ab270c3899
Merge pull request #3183 from dzhwinter/add_op_gradient
...
"add rowwise add backward op"
8 years ago
dangqingqing
70285cce32
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into cross_entropy
8 years ago
qiaolongfei
46d30ec680
init minst.py
8 years ago
qiaolongfei
230e613c6f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix-sgd
8 years ago
dongzhihong
cef27dab47
"add fixl"
8 years ago
dongzhihong
448d4db5c1
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_op_gradient
8 years ago
dongzhihong
88360100bf
Merge remote-tracking branch 'origin/develop' into mul_op
8 years ago
gangliao
62aedcee31
Merge pull request #3553 from reyoung/feature/unittest_for_mean_grad
...
Add MeanOp's Gradient Test And Fix Mean Op Gradient
8 years ago
Yu Yang
e28e007373
Enable test_sgd_op
8 years ago
Yu Yang
7f8c3f8214
Add MeanOp's Gradient Test And Fix Mean Op Gradient
8 years ago
qingqing01
c68bfc30a8
Merge pull request #3476 from qingqing01/bp_test
...
Compare the gradient consistency between GPU and CPU calculations
8 years ago
dangqingqing
5181aefc6b
tune max relative error for sigmoid op unit test.
8 years ago
dangqingqing
18dcc1c0bc
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into bp_test
8 years ago
dangqingqing
a28a5564d2
add more comments and fix code style.
8 years ago
zchen0211
6075928d55
gather op added
8 years ago
Yu Yang
f15e083098
Remove std::shared_ptr in Python & C++
...
* Also simplify pybind implementation by using OperatorBase as holder
type.
8 years ago
superjom
1543eeb4ce
init
8 years ago
zchen0211
4d2adab772
gather op added with python unittest
8 years ago
zchen0211
323d4233f3
gather op added with python unittest
8 years ago
dangqingqing
26475cd9ba
Use clipping log in cuda kernel, making it same with CPU.
8 years ago
dangqingqing
49aa2c042c
Implement GPU kernel for cross entropy operator.
8 years ago
dongzhihong
4c9699c5f8
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into mul_op
8 years ago
Yan Chunwei
0079fa3256
Rnn make stepnet member ( #3469 )
...
* make stepnet member
* add pybind support
* fix Inputs Outputs
* remove unique_ptr
8 years ago
dangqingqing
9a0eedf5d4
fix bug.
8 years ago
dangqingqing
01d9134067
Add test_gradient_checker.py
8 years ago
dangqingqing
84d6434d53
Compare the gradient consistency between GPU and CPU calculations.
8 years ago
dongzhihong
43ba24e051
Merge remote-tracking branch 'origin/develop' into add_op_gradient
8 years ago
dongzhihong
632b320e9d
"refine argument with new style "
8 years ago
dongzhihong
426d7328a0
Merge remote-tracking branch 'origin/develop' into mul_op
8 years ago
Yu Yang
81f5f86140
Merge pull request #3322 from wangkuiyi/refactorize_framework_proto
...
Refactorize framework/*.proto
8 years ago
Yu Yang
4a604c2651
Polish Our code by YuYang's review
8 years ago
superjom
a0b49a6c5b
add test to CMAKE
8 years ago
superjom
0d1bc8ab9b
fix res
8 years ago
superjom
b1b71eab6c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rnn_forward_result_test
8 years ago
Yu Yang
610a25844f
Fix all unit tests in Python
8 years ago
Yu Yang
d6d46412ef
Merge branch 'develop' of github.com:baidu/Paddle into final_fixes
8 years ago
Yi Wang
0dc75ab3ef
Merge pull request #3410 from jacquesqiao/numeric-gradient-design
...
add auto gradient check design doc
8 years ago
Yi Wang
96fc9e7d1b
Merge pull request #11 from reyoung/fix_python_tests
...
Fix python unit tests
8 years ago
Yu Yang
133a8ea7fd
Polish Error message
8 years ago
Yu Yang
9a592ec3aa
Remove FC Op, since it should be added in Python side
8 years ago
Yu Yang
c99f84aced
Fix python unit tests
8 years ago
qiaolongfei
f485a9bc50
add auto gradient check design doc
8 years ago
gangliao
be473a62eb
Merge pull request #3357 from jacquesqiao/python-test
...
support python test without installation python package
8 years ago
Yu Yang
7fab7ddd7d
Merge branch 'develop' of github.com:baidu/Paddle into feature/refactorize_framework_proto
8 years ago
qingqing01
7202f425dd
Merge branch 'refactorize_framework_proto' into feature/refactorize_framework_proto
8 years ago
Yu Yang
3f34ff8f9f
Comment test_gaussian_random_op for hotfix
8 years ago
dongzhihong
2ddb11222a
"on hold"
8 years ago
dongzhihong
7c0cb0c790
"fix ci launch"
8 years ago
dzhwinter
56faf51343
Merge pull request #3060 from dzhwinter/random_op
...
Random op
8 years ago
dongzhihong
68bfc3ff96
"add python test"
8 years ago
qingqing01
665e1a335b
Update grad_op_builder after refactoring framework proto.
8 years ago
liaogang
5e5c441245
Enable Python Unit Test before make install
8 years ago
dongzhihong
f702e7977d
"relauch ci"
8 years ago
Yu Yang
f0a85b0805
Rename __is_close -> assert_is_close()
8 years ago
Yu Yang
c957445c72
A better error message for gradient checker
...
* Give which parameter, which element are wrong. And what max_diff is.
8 years ago
dongzhihong
bbd7378b43
"ci job failed weired. restart ci job."
8 years ago
dongzhihong
6bac3e17b5
"remove unused test net modified"
8 years ago
dongzhihong
d98e299d3b
"keep same with uniform random op"
8 years ago
dongzhihong
b7ee1e7d9c
"backward check todo"
8 years ago
dongzhihong
6535a7b001
Merge remote-tracking branch 'origin/develop' into random_op
8 years ago
Qiao Longfei
e31a469ee0
add gradient test framework ( #3226 )
...
* init grad op checker
* can run
* add GradeChecker class
* use get_numeric_gradient
* refine code
* add softmax and cross entropy auto grad test
* use close to judge op_grad and numeric_grad
* add cpu and gpu compare
* add comments
* add support_gpu
* fix allclose
* fix name error and symplify code
* optimize gradient checker
* add test_cross_entropy_op
* update gradient_checker.py
* optimize code
* use random.uniform instead of random.random
* fix type bug
* optimize check_grad
* put SupportGPU into OperatorBase
* typo
8 years ago
dongzhihong
23ac845921
Merge remote-tracking branch 'origin/develop' into random_op
8 years ago
superjom
e9a92e3ed8
add fc test
8 years ago
superjom
001b62a4c7
finish simple rnn in python
8 years ago
dongzhihong
8804b242d8
Merge remote-tracking branch 'origin/develop' into random_op
8 years ago
dongzhihong
52d2ebdaef
"test gaussian random in python side"
8 years ago
Yu Yang
b861c01963
Merge branch 'develop' into feature/uniform_random_op
8 years ago
fengjiayi
e7b3e13959
Rewrite test based on new python test format
8 years ago
fengjiayi
5d2b3fb09d
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dev_add_FillZerosLikeOp_test
8 years ago
Yu Yang
ffd6c3cea6
Merge branch 'develop' into feature/change_op_creation
8 years ago
Yu Yang
e5847924f3
Merge branch 'develop' of github.com:baidu/Paddle into feature/uniform_random_op
8 years ago
Qiao Longfei
493396d81c
add support_gpu ( #3304 )
...
* add support_gpu
* fix allclose
* fix name error and symplify code
8 years ago
dongzhihong
58561d8f56
Merge remote-tracking branch 'origin/develop' into random_op
8 years ago
Yu Yang
d7f0eb6baf
Merge branch 'feature/change_op_creation' into feature/uniform_random_op
8 years ago
Yu Yang
460326f4b2
Fix CI Test
8 years ago
Yi Wang
efa50a4525
Merge pull request #3181 from qingqing01/sigmoid_bp
...
Sigmoid backward implementation.
8 years ago
Yu Yang
9f816352e5
Follow comments
8 years ago
Yan Chunwei
7665bdba13
Rnn forward logic test ( #3291 )
...
* finish forward debug
8 years ago
Yu Yang
5d074c917c
Merge branch 'develop' into feature/change_op_creation
8 years ago
gangliao
ec2c753c3d
Merge pull request #3290 from PaddlePaddle/cblas_new
...
Import HPC linear algebra libs as cblas target for cc_library deps
8 years ago
Yu Yang
fd0bdb4f8a
Merge branch 'feature/change_op_creation' into feature/uniform_random_op
8 years ago
dangqingqing
9f490c7748
update to develop branch.
8 years ago
liaogang
7ecdf6ad93
Add py_test
8 years ago
Yu Yang
e376bda42c
Add uniform random operator
...
It can be run both CPU/GPU. configure attributes are:
* min: the min value of uniform random
* max: the max value of uniform random
* dims: the dimension of output tensor
* seed: the random seed of uniform random. 0 means generate a seed each
time.
8 years ago
dangqingqing
f72cefabce
fix typo and resolve conflicts.
8 years ago
Yu Yang
a1e16bb5d3
Merge branch 'develop' into feature/change_op_creation
8 years ago
dongzhihong
2447c34a0e
merge origin/develop
8 years ago
Yan Chunwei
c72253127f
crossentropy grad op ( #3186 )
...
* init cross entropy graident
* add crossentropy grad op
* remove details
* fix static compile
8 years ago
QI JUN
10ee3dcbcf
Merge pull request #3248 from QiJune/refine_op_test_compare
...
use isclose instead of assert_almost_equal
8 years ago
Yu Yang
b4ebb3c85c
Change attr_type_pb2 to attribute_pb2
...
Make ci pass
8 years ago
fengjiayi
9b0fce516a
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dev_add_FillZerosLikeOp_test
8 years ago
qijun
dcdd2903fe
use isclose instead of assert_almost_equal
8 years ago
dangqingqing
7fdfe1a9c7
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into unit_test
8 years ago
dangqingqing
c540aa040f
Refine unit test in op_test_util
8 years ago
Yu Yang
89d33ff83f
Complete chagne op creation method.
...
Currently use `Operator("fc", X="x", W='w1', B='b1')` as operator
creation method.
Fix #3198
8 years ago
Yu Yang
a239418bdf
Fix unittest for operator.py
...
Rename operator.py to op.py because it is conflict with protobuf
8 years ago
Yu Yang
53f85df1ab
Start doing `python.framework.operator`
8 years ago
Yu Yang
aaf2d66db8
Merge branch 'develop' of github.com:baidu/Paddle into gradient_check_utils
8 years ago
fengjiayi
df84e39a00
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dev_add_FillZerosLikeOp_test
8 years ago
Qiao Longfei
d953611e86
Softmax grad op ( #3164 )
...
* init softmax grad op
* add compute code
* export Backward to python
* update test ,export op.type to python
* update python test, fix compute bug
* update unit test
* use eigen
* optimize eigen code
* add gpu test
* register softmax_grad GPU kernel and fix test bug
* typo
* follow comments
8 years ago
dangqingqing
4eb25b4793
update code.
8 years ago
Yu Yang
133541ee41
Merge codes
8 years ago
Yu Yang
fbcadb75c6
Merge branch 'develop' of github.com:baidu/Paddle into gradient_check_utils
8 years ago
fengjiayi
589c3d864b
Rewirte test based on python test frameworks
8 years ago
Qiao Longfei
cc6c33b8b2
export Backward to python ( #3174 )
...
* export Backward to python
8 years ago
dangqingqing
bd01cea1f3
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into sigmoid_bp
8 years ago
dangqingqing
0560733c2e
Add sigmoid backward implenmention.
8 years ago
Yu Yang
3e812383bc
Merge branch 'develop' of github.com:baidu/Paddle into gradient_check_utils
8 years ago
Yu Yang
a0590004ce
Add __all__ in `gradient_checker.py`
8 years ago
qijun
341d1880ee
Merge remote-tracking branch 'baidu/develop' into op_gpu_test
8 years ago
Yu Yang
fcc28ccea2
Add comments
8 years ago
Yu Yang
7c42aad412
Initialize Gradient Checker
...
Add get_numeric_gradient API and its unittest.
8 years ago
qijun
81cc7a3227
merge baidu/develop
8 years ago
fengjiayi
244c343b66
Fix a test error
8 years ago
fengjiayi
3a8017d148
Merge branch 'backward_dev' into dev_add_FillZerosLikeOp_test
8 years ago
fengjiayi
c59fe7a039
Add unittest for FillZerosLikeOp
8 years ago
fengjiayi
8bd73159c7
Add unittest for `FillZerosLikeOp`
8 years ago
liaogang
c36a093c5e
Fix conflict
8 years ago
liaogang
1e676f684d
Add mean op unit test in python
8 years ago
Yu Yang
5d134a03f1
Refine remove std::shared_ptr in Scope
...
* Make interface of Operator to `const Scope&`
8 years ago
qijun
cf5ac5888e
reduce gpu memory allocation in op_test
8 years ago
qijun
61f94f0002
add EIGEN_USE_GPU macro to op.cu file
8 years ago
qijun
4a1f7bd21f
add gpu python op test
8 years ago
qijun
4cc42171db
merge baidu/develop
8 years ago
dongzhihong
933e55eb06
fix conflict
8 years ago
dongzhihong
47556689d4
"remove unused code"
8 years ago
dongzhihong
4d8ece8a3c
"update"
8 years ago
Yan Chunwei
aee0d3ec5f
RecurrentOp implementation ( #2890 )
...
* add rnn op interfaces
* add Run
* rename state -> memory
* change state -> memory
* make compilable
* add .cc
* init test
* add op fake implementation
* add CreateStepNet and CreateScopes implementation.
* add TODO list
* init memory attributes.
* add LinkMemories
* add PlainNet fake implementation
* Use std::shared_ptr<Scope> in the OpRunContext.
* add test
* disable mutable_data
* finist segmentInput function
* enable mutable_data with a trick
* RNNOp test.
* enable LinkMemories with mutable_data
* update SegmentInput function with comments
* finish ConcatOutput function
* reformat inputs and attributes
boot_memories
* Refine unit test.
* Refine unit test.
* modify inlinks.
* add OpDesc to Net
* fix bug and update unit test.
* move step scopes from inputs to outputs
* fix merge conflict, update SegmentInput function
* add RecurrentOpProtoAndCheckerMaker.
* clean the codes
* Abstract GetStepScopes and GetMaxSeqLen function
* refine LinkMemories
* Refine code and add some comments.
* add backward core
* update for develop branch.
* add forward core
* add forward algorithm
* Add RecurrentGradientAlgorithm implenmention.
* use CopyFrom and Slice function in RecurrentOp
* add unit test for LinkMemories.
* fix unit test.
* use the latest tensor.h, solve conflict
* add maker
* move SegmentInput and ConcatOutput to details nameplace
* unit test for RecurrentGradientAlgorithm.
* apply OperatorBase
* apply net operator.
* move memorys to attributes
* add RecurrentGradientOp
* open test unit test in recurrent_network_op_test.
* revert some files.
* add RecurrentArgument and Link struct to simplify member variable.
* rename.
* move recurrent_op from framework to operators
* add RecurrentGradientOp Init
* fix name
* fix Link.interal/external name
* use namespace operators instead of framework
* clean the code
* use the latest add_op and mul_op, don't test backward now
* Remove ScopePtr and OperatorPtr
* add get_net to pybind
* add test_recurrent_op.py
* add random into gen_tensor
* update to develop branch and refine some code.
* add some comments.
8 years ago
dongzhihong
a22567ebef
"fix almost equal error"
8 years ago
dongzhihong
984225ecf1
"fix operator"
8 years ago
qijun
358261f0bd
fix gpu build error
8 years ago
Yu Yang
754f0c68da
Fix unittest
8 years ago
dongzhihong
32c15a2919
"random op test"
8 years ago
Yu Yang
b80590d70b
Remove test_plain_net
8 years ago
Yu Yang
0ceeacbe45
Make Scope can lookup variable name by variable
...
* Refine unittest also
8 years ago
Yu Yang
0ab678e9e2
Add unittest for network
8 years ago
Yu Yang
c14f3e8ff2
Merge branch 'develop' into feature/middle_level_net_api
8 years ago
Yu Yang
9e4fac1ef4
Complete Add Op
8 years ago
Yu Yang
684563660b
Init commit
8 years ago
Yu Yang
1294b3c53e
Expose Net to Python ( #2967 )
...
* Expose Net to Python
* Expose PlainNet to Python, make python can add_op, complete_add_op
* Provide a low level api to manipulate Net
* Unittest for Net::DebugString
8 years ago
qijun
06acd6d0cb
add unittest for some basic OpKernels
8 years ago
Qiao Longfei
2685765905
add cross-entropy-op ( #2965 )
...
* add cross-entropy-op
* add infershape and compute
* implement Infershape and compute of onehotcrossentropy op
8 years ago
Yu Yang
a98346f4cd
Add comment to `OpTestMeta` ( #2968 )
8 years ago
Qiao Longfei
e3b27d1998
Add sgd op ( #2950 )
...
* a simplest SGD op
8 years ago
Yu Yang
21baa94b04
Merge branch 'feature/expose_net_op' into feature/middle_level_net_api
8 years ago
Yu Yang
0380bfb3cf
Expose Net to Python
...
* Expose PlainNet to Python, make python can add_op, complete_add_op
* Provide a low level api to manipulate Net
* Unittest for Net::DebugString
8 years ago
Yu Yang
3402b6ad39
Add Unittest of add_two_op
8 years ago
Yu Yang
d3373c5b85
Skeleton Of fully connected operator
...
* Fc operator is a grouped operator, which combined by may internal
operators.
* InferShape & Run a FC operator in Python.
8 years ago
Yu Yang
a89c7ffa94
Make Tensor <--> Numpy interactive in tensor.h
...
* Follow review comments to seperate Tensor Numpy interactive methods in
tensor.h.
* Simplify logic for `CastToPyBufferImpl`, make it as one struct and in
details namespace.
* Remove `Scope` expose in Python, since it currently is useless.
* Remove some debug functions.
8 years ago
Yu Yang
bde90be71b
Read/Write a Tensor Python
...
Basically following
http://pybind11.readthedocs.io/en/stable/advanced/pycpp/numpy.html
* Use buffer protocol to return a view of Tensor. It can be cast to
numpy array in Python.
* Set a numpy array to a tensor.
8 years ago
Yu Yang
9e0c6800c5
Python Generate OpCreation Methods by OpProto
...
All OpCreation method are generated by
`create_op_creation_methods::__bootstrap__` method, and stores in
`op_creations` object and its methods.
There are three parts to implement this feature.
1. Get all registered `OpProto` from C++ side. It is implemented in
`get_all_op_protos` method.
1. Create a function to convert `kwargs` to `OpDesc` base on each op's
`OpProto`. The `OpDescCreationMethod` class.
1. Convert `OpProto` to `docstring` by `get_docstring_from_op_proto`
method.
All three methods are unit tested. The `__bootstrap__` just combines
them together and create a method in runtime.
For details, please reference the doc string in
`create_op_creation_methods.py` and the unit test
`test_op_creation_methods.py`.
8 years ago
Yu Yang
a76f7ed2eb
Get OpProtos in Python
...
* PyBind and SWIG of paddle cannot be load in a single Python process,
lazy import all SWIG library of Paddle. Otherwise, the glog, gflags
are imported twice in a same Python process.
* Note that all PyBind11 return C++ std::string as an unicode. For
protobuf, it is need be cast to `str` before use them.
* Add unit test for Get `OpProtos`
8 years ago
Yu Yang
8da5587205
Init commit
8 years ago
Yu Yang
d027f47d7d
Default scope function
...
`Paddle` manages Scope as programming language's scope. It just a
thread-local stack of Scope. Top of that stack is current scope, the
bottom of that stack is all scopes' parent.
Invoking `create_var/get_var` can `create/get` variable in current
scope. Invoking `enter_local_scope/leave_local_scope` can create or
destroy local scope.
A `scoped_function` will take a `function` as input. That function will
be invoked in a new local scope.
8 years ago
Yu Yang
27b196ba6d
Expose paddle.framework by pybind11 ( #2793 )
...
* Expose paddle.framework by pybind11
* Export paddle.framework.{Scope, Variable} to paddle.v2.framework.core.
* See python/paddle/v2/framework/tests/test_scope.py for Python usage
* See paddle/pybind/pybind.cc for C++ bind code.
* add copyright
8 years ago
Yu Yang
e2ea1f42e9
Generate python protobufs for paddle.v2.framework
...
Python should be able to manipulate Protobuf message because:
1. Python's `create_op_creation_methods` take the `OpProto` array to
generate all `op_creation_methods` in RunTime.
2. All `op_creation_methods` will create an `OpDesc` and pass it to
Paddle C++ method `CreateOp` and return the Op handle.
Here is the list of what is added in this commit:
* Add `protobuf_generate_python` if it is not defined.
* Before cmake 3.4, `protobuf_generate_python` is not defined. Just
copy the implementation of that function in `protobuf.cmake`
* Add `py_proto_compile` function in `cmake/generic.cmake`.
* It follows bazel's API interface.
* https://github.com/pubref/rules_protobuf#rules
* Add an empty package named `paddle.v2.framework`, all python code of
`paddle::framework` will be in that package.
* Generate protobuf's python module `__init__.py` by `touch` while
compiling.
* Change setup.py.in, make `paddle.v2.framework.proto` uses the
generated protobuf pythons.
8 years ago