tensor-tang
|
7483087c8c
|
enable mkldnn_softmax
|
8 years ago |
|
tensor-tang
|
eb26fdce46
|
add python interface for mkldnn_relu and mkldnn_tanh
|
8 years ago |
|
tensor-tang
|
971acff749
|
add python interface for mkldnn_pool
|
8 years ago |
Tao Luo
|
654344b94c
|
Merge pull request #4032 from tensor-tang/mkldnn-conv
Add MKLDNNConvLayer
|
8 years ago |
|
tensor-tang
|
66fdbd0cee
|
add some comment and simplify some code
|
8 years ago |
caoying03
|
1f839a6618
|
fix bug in prelu parsing.
|
8 years ago |
|
tensor-tang
|
44acc7514a
|
add python interface for mkldnn_conv
|
8 years ago |
wanghaoshuang
|
253b19ed9a
|
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_warning
|
8 years ago |
|
wanghaoshuang
|
5bd3fbeef8
|
Fix switch layer attribute name
|
8 years ago |
chengduo
|
0be349496f
|
Merge pull request #3594 from chengduoZH/Adapting_to_the_BatchNorm_structure_to_support_3D_data
Adapting to the BatchNorm structure to support 3D data
|
8 years ago |
chengduoZH
|
80a8e91fb8
|
fix order
|
8 years ago |
|
chengduoZH
|
aea05b6e95
|
add param mean_var_names
|
8 years ago |
|
chengduoZH
|
26638e9cab
|
fix batch_norm parameter share
|
8 years ago |
|
wanghaoshuang
|
de145b0aa5
|
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into pixel_softmax_layer
|
8 years ago |
lispc
|
5d9478094d
|
PyDataProvider2.InputType repr refine style
|
8 years ago |
|
chengduoZH
|
4cb2966d7b
|
fix config_parser.py(concat_layer and addto_layer)
|
8 years ago |
|
whs
|
a162ebce8b
|
Merge branch 'develop' into pixel_softmax_layer
|
8 years ago |
|
chengduoZH
|
eaf23cb1e8
|
fix ModelConfig.proto, addto_layer and concat_layer
|
8 years ago |
|
Zhuo Zhang
|
879866cc56
|
add PyDataProvider2.InputType pretty print function
|
8 years ago |
|
chengduoZH
|
a55dd22649
|
fix conflict
|
8 years ago |
|
chengduoZH
|
6374831966
|
fix conflict
|
8 years ago |
|
chengduoZH
|
a357bd6fe5
|
Fix conflict and Add test_pooling3D_layer.protostr
|
8 years ago |
|
chengduoZH
|
455d2bd7b1
|
fix conflict
|
8 years ago |
|
chengduoZH
|
536dbc0cb6
|
fix conflict
|
8 years ago |
|
chengduoZH
|
3b0e43aa6a
|
add config parse
|
8 years ago |
|
caoying03
|
3d1b87193d
|
Merge branch 'develop' into cross_entropy_over_beam
|
8 years ago |
|
chengduoZH
|
43da7675b3
|
fix conflict
|
8 years ago |
|
chengduoZH
|
4dcc533206
|
fix conflict
|
8 years ago |
|
chengduoZH
|
b1c0bad9fe
|
Add config parser for pooling3D
|
8 years ago |
|
chengduoZH
|
2710584ff1
|
fix above comments
|
8 years ago |
|
Luo Tao
|
acd8a22ed1
|
Merge branch 'develop' into huber_loss
|
8 years ago |
|
caoying03
|
3d12a610ca
|
Merge branch 'develop' into cross_entropy_over_beam
|
8 years ago |
|
Luo Tao
|
7596191821
|
Merge branch 'develop' into huber_loss
|
8 years ago |
|
wanghaoshuang
|
e286b950a5
|
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dilate_conv
|
8 years ago |
|
caoying03
|
74d3ca8bab
|
Merge branch 'develop' into cross_entropy_over_beam
|
8 years ago |
Cao Ying
|
ab6b3c481a
|
Merge pull request #3367 from lcy-seso/add_sequence_slice_layer
Add a sequence slice layer.
|
8 years ago |
|
caoying03
|
5e59ca7ccc
|
fix config helper.
|
8 years ago |
|
wanghaoshuang
|
e3342ff8e7
|
Fix android build error.
|
8 years ago |
|
chengduoZH
|
f715c740bf
|
Add_config_parser_for_Conv3D_DeConv3D
|
8 years ago |
|
caoying03
|
bc6bae8d53
|
Merge branch 'develop' into add_sequence_slice_layer
|
8 years ago |
|
caoying03
|
82e4fab4e3
|
follow comments.
|
8 years ago |
|
wanghaoshuang
|
2c8b3c4430
|
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dilate_conv
|
8 years ago |
|
wanghaoshuang
|
d8cd67dd1e
|
Make cudnn convolution layer and projection support for dilation.
|
8 years ago |
|
caoying03
|
25083de998
|
Merge branch 'develop' into cross_entropy_over_beam
|
8 years ago |
xuwei06
|
d7b80f03b0
|
Correctly handle width and height for some layers
|
8 years ago |
|
Luo Tao
|
3065cb2625
|
add huber_regression_cost
|
8 years ago |
guosheng
|
7d2ef02a99
|
Add ScaleShiftLayer
|
8 years ago |
|
Luo Tao
|
e6db484d15
|
make clear that current huber_cost is for two-classification
|
8 years ago |
|
caoying03
|
44ae44da49
|
add configuratioin helpers.
|
8 years ago |
|
caoying03
|
b7359ee3ce
|
Merge branch 'develop' into add_sequence_slice_layer
|
8 years ago |
