Skip to content

P
Paddle

机器未来 / Paddle
与 Fork 源项目一致

Fork自 PaddlePaddle / Paddle

通知 1
Star 1
Fork 0
P
Paddle
提交 95e5768b 编写于 作者: Z zhongpu 提交者： Jiabin Yang
浏览文件
操作

update conv, fc, pool op for dygraph, test=develop (#20132)

上级 9ca417f1
隐藏空白更改
内联 并排
Showing with 224 addition and 171 deletion
paddle/fluid/API.spec
浏览文件 @ 95e5768b
...@@ -592,7 +592,7 @@ paddle.fluid.dygraph.Layer.train (ArgSpec(args=['self'], varargs=None, keywords= ...@@ -592,7 +592,7 @@ paddle.fluid.dygraph.Layer.train (ArgSpec(args=['self'], varargs=None, keywords=
paddle.fluid.dygraph.__impl__ (ArgSpec(args=['func'], varargs=None, keywords=None, defaults=()), ('document', '75d1d3afccc8b39cdebf05cb1f5969f9')) paddle.fluid.dygraph.__impl__ (ArgSpec(args=['func'], varargs=None, keywords=None, defaults=()), ('document', '75d1d3afccc8b39cdebf05cb1f5969f9'))
paddle.fluid.dygraph.guard (ArgSpec(args=['place'], varargs=None, keywords=None, defaults=(None,)), ('document', '7071320ffe2eec9aacdae574951278c6')) paddle.fluid.dygraph.guard (ArgSpec(args=['place'], varargs=None, keywords=None, defaults=(None,)), ('document', '7071320ffe2eec9aacdae574951278c6'))
paddle.fluid.dygraph.to_variable (ArgSpec(args=['value', 'block', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '0e69fa3666f15dd01b6e3e270b9371cd')) paddle.fluid.dygraph.to_variable (ArgSpec(args=['value', 'block', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '0e69fa3666f15dd01b6e3e270b9371cd'))
paddle.fluid.dygraph.Conv2D ('paddle.fluid.dygraph.nn.Conv2D', ('document', '0b6acb9cc7fbb4f5b129e1f6dd985581')) paddle.fluid.dygraph.Conv2D ('paddle.fluid.dygraph.nn.Conv2D', ('document', '10915f3c643e232d9c6789ce20a96869'))
paddle.fluid.dygraph.Conv2D.__init__ (ArgSpec(args=['self', 'name_scope', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'dtype'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, 'float32')), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.Conv2D.__init__ (ArgSpec(args=['self', 'name_scope', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'dtype'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, 'float32')), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.Conv2D.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1')) paddle.fluid.dygraph.Conv2D.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1'))
paddle.fluid.dygraph.Conv2D.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995')) paddle.fluid.dygraph.Conv2D.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995'))
...@@ -626,7 +626,7 @@ paddle.fluid.dygraph.Conv3D.set_dict (ArgSpec(args=['self', 'stat_dict', 'includ ...@@ -626,7 +626,7 @@ paddle.fluid.dygraph.Conv3D.set_dict (ArgSpec(args=['self', 'stat_dict', 'includ
paddle.fluid.dygraph.Conv3D.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac')) paddle.fluid.dygraph.Conv3D.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac'))
paddle.fluid.dygraph.Conv3D.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62')) paddle.fluid.dygraph.Conv3D.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62'))
paddle.fluid.dygraph.Conv3D.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.Conv3D.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.Pool2D ('paddle.fluid.dygraph.nn.Pool2D', ('document', '50e6fd200e42859daf2924ecb0561ada')) paddle.fluid.dygraph.Pool2D ('paddle.fluid.dygraph.nn.Pool2D', ('document', 'ea0b4ef5fd7befb7841cc2f17e66007a'))
paddle.fluid.dygraph.Pool2D.__init__ (ArgSpec(args=['self', 'name_scope', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'exclusive', 'dtype'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, True, VarType.FP32)), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.Pool2D.__init__ (ArgSpec(args=['self', 'name_scope', 'pool_size', 'pool_type', 'pool_stride', 'pool_padding', 'global_pooling', 'use_cudnn', 'ceil_mode', 'exclusive', 'dtype'], varargs=None, keywords=None, defaults=(-1, 'max', 1, 0, False, True, False, True, VarType.FP32)), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.Pool2D.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1')) paddle.fluid.dygraph.Pool2D.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1'))
paddle.fluid.dygraph.Pool2D.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995')) paddle.fluid.dygraph.Pool2D.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995'))
...@@ -643,7 +643,7 @@ paddle.fluid.dygraph.Pool2D.set_dict (ArgSpec(args=['self', 'stat_dict', 'includ ...@@ -643,7 +643,7 @@ paddle.fluid.dygraph.Pool2D.set_dict (ArgSpec(args=['self', 'stat_dict', 'includ
paddle.fluid.dygraph.Pool2D.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac')) paddle.fluid.dygraph.Pool2D.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac'))
paddle.fluid.dygraph.Pool2D.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62')) paddle.fluid.dygraph.Pool2D.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62'))
paddle.fluid.dygraph.Pool2D.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.Pool2D.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.FC ('paddle.fluid.dygraph.nn.FC', ('document', '2f73ae00e57c67454c6aa7e911d9bfd6')) paddle.fluid.dygraph.FC ('paddle.fluid.dygraph.nn.FC', ('document', '6f4d1855a05f99f5500e042212e5c605'))
paddle.fluid.dygraph.FC.__init__ (ArgSpec(args=['self', 'name_scope', 'size', 'num_flatten_dims', 'param_attr', 'bias_attr', 'act', 'is_test', 'dtype'], varargs=None, keywords=None, defaults=(1, None, None, None, False, 'float32')), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.FC.__init__ (ArgSpec(args=['self', 'name_scope', 'size', 'num_flatten_dims', 'param_attr', 'bias_attr', 'act', 'is_test', 'dtype'], varargs=None, keywords=None, defaults=(1, None, None, None, False, 'float32')), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.FC.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1')) paddle.fluid.dygraph.FC.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1'))
paddle.fluid.dygraph.FC.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995')) paddle.fluid.dygraph.FC.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995'))
...@@ -779,7 +779,7 @@ paddle.fluid.dygraph.BilinearTensorProduct.set_dict (ArgSpec(args=['self', 'stat ...@@ -779,7 +779,7 @@ paddle.fluid.dygraph.BilinearTensorProduct.set_dict (ArgSpec(args=['self', 'stat
paddle.fluid.dygraph.BilinearTensorProduct.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac')) paddle.fluid.dygraph.BilinearTensorProduct.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac'))
paddle.fluid.dygraph.BilinearTensorProduct.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62')) paddle.fluid.dygraph.BilinearTensorProduct.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62'))
paddle.fluid.dygraph.BilinearTensorProduct.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.BilinearTensorProduct.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.Conv2DTranspose ('paddle.fluid.dygraph.nn.Conv2DTranspose', ('document', 'cf23c905abc00b07603dfa71a432d6f7')) paddle.fluid.dygraph.Conv2DTranspose ('paddle.fluid.dygraph.nn.Conv2DTranspose', ('document', 'cb5e718ff190ee82e9bd144585dd4707'))
paddle.fluid.dygraph.Conv2DTranspose.__init__ (ArgSpec(args=['self', 'name_scope', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None)), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.Conv2DTranspose.__init__ (ArgSpec(args=['self', 'name_scope', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None)), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.Conv2DTranspose.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1')) paddle.fluid.dygraph.Conv2DTranspose.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1'))
paddle.fluid.dygraph.Conv2DTranspose.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995')) paddle.fluid.dygraph.Conv2DTranspose.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995'))
...@@ -847,7 +847,7 @@ paddle.fluid.dygraph.SpectralNorm.set_dict (ArgSpec(args=['self', 'stat_dict', ' ...@@ -847,7 +847,7 @@ paddle.fluid.dygraph.SpectralNorm.set_dict (ArgSpec(args=['self', 'stat_dict', '
paddle.fluid.dygraph.SpectralNorm.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac')) paddle.fluid.dygraph.SpectralNorm.state_dict (ArgSpec(args=['self', 'destination', 'include_sublayers'], varargs=None, keywords=None, defaults=(None, True)), ('document', '9d689f44592cd22812c7ec06a9654eac'))
paddle.fluid.dygraph.SpectralNorm.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62')) paddle.fluid.dygraph.SpectralNorm.sublayers (ArgSpec(args=['self', 'include_sublayers'], varargs=None, keywords=None, defaults=(True,)), ('document', '00a881005ecbc96578faf94513bf0d62'))
paddle.fluid.dygraph.SpectralNorm.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.SpectralNorm.train (ArgSpec(args=['self'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.TreeConv ('paddle.fluid.dygraph.nn.TreeConv', ('document', '6e175a7bf2a43ae6c0f3a8a54bd69afe')) paddle.fluid.dygraph.TreeConv ('paddle.fluid.dygraph.nn.TreeConv', ('document', 'cd21d9c15581cf7339ad04794beaa85e'))
paddle.fluid.dygraph.TreeConv.__init__ (ArgSpec(args=['self', 'name_scope', 'output_size', 'num_filters', 'max_depth', 'act', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1, 2, 'tanh', None, None, None)), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.dygraph.TreeConv.__init__ (ArgSpec(args=['self', 'name_scope', 'output_size', 'num_filters', 'max_depth', 'act', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1, 2, 'tanh', None, None, None)), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.dygraph.TreeConv.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1')) paddle.fluid.dygraph.TreeConv.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1'))
paddle.fluid.dygraph.TreeConv.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995')) paddle.fluid.dygraph.TreeConv.add_sublayer (ArgSpec(args=['self', 'name', 'sublayer'], varargs=None, keywords=None, defaults=None), ('document', '839ff3c0534677ba6ad8735c3fd4e995'))
......
python/paddle/fluid/dygraph/nn.py
浏览文件 @ 95e5768b
...@@ -34,16 +34,18 @@ __all__ = [ ...@@ -34,16 +34,18 @@ __all__ = [
class Conv2D(layers.Layer): class Conv2D(layers.Layer):
""" """
This interface is used to construct a callable object of the ``Conv2D`` class.
For more details, refer to code examples.
The convolution2D layer calculates the output based on the input, filter The convolution2D layer calculates the output based on the input, filter
and strides, paddings, dilations, groups parameters. Input and and strides, paddings, dilations, groups parameters. Input and
Output are in NCHW format, where N is batch size, C is the number of Output are in NCHW format, where N is batch size, C is the number of
channels, H is the height of the feature, and W is the width of the feature. the feature map, H is the height of the feature map, and W is the width of the feature map.
Filter is in MCHW format, where M is the number of output image channels, Filter's shape is [MCHW] , where M is the number of output feature map,
C is the number of input image channels, H is the height of the filter, C is the number of input feature map, H is the height of the filter,
and W is the width of the filter. If the groups is greater than 1, and W is the width of the filter. If the groups is greater than 1,
C will equal the number of input image channels divided by the groups. C will equal the number of input feature map divided by the groups.
Please refer to UFLDL's `convolution Please refer to UFLDL's `convolution
<http://ufldl.stanford.edu/tutorial/supervised/FeatureExtractionUsingConvolution/>` <http://ufldl.stanford.edu/tutorial/supervised/FeatureExtractionUsingConvolution/>`_
for more detials. for more detials.
If bias attribution and activation type are provided, bias is added to the If bias attribution and activation type are provided, bias is added to the
output of the convolution, and the corresponding activation function is output of the convolution, and the corresponding activation function is
...@@ -53,14 +55,14 @@ class Conv2D(layers.Layer): ...@@ -53,14 +55,14 @@ class Conv2D(layers.Layer):
.. math:: .. math::
Out = \sigma (W \\ast X + b) Out = \\sigma (W \\ast X + b)
Where: Where:
* :math:`X`: Input value, a tensor with NCHW format. * :math:`X`: Input value, a ``Tensor`` with NCHW format.
* :math:`W`: Filter value, a tensor with MCHW format. * :math:`W`: Filter value, a ``Tensor`` with shape [MCHW] .
* :math:`\\ast`: Convolution operation. * :math:`\\ast`: Convolution operation.
* :math:`b`: Bias value, a 2-D tensor with shape [M, 1]. * :math:`b`: Bias value, a 2-D ``Tensor`` with shape [M, 1].
* :math:`\\sigma`: Activation function. * :math:`\\sigma`: Activation function.
* :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different. * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different.
...@@ -84,48 +86,52 @@ class Conv2D(layers.Layer): ...@@ -84,48 +86,52 @@ class Conv2D(layers.Layer):
W_{out}&= \\frac{(W_{in} + 2 * paddings[1] - (dilations[1] * (W_f - 1) + 1))}{strides[1]} + 1 W_{out}&= \\frac{(W_{in} + 2 * paddings[1] - (dilations[1] * (W_f - 1) + 1))}{strides[1]} + 1
Parameters: Parameters:
name_scope(str) : The name for this class. name_scope(str): The name for this class.
num_filters(int): The number of filter. It is as same as the output num_filters(int): The number of filter. It is as same as the output
image channel. feature map.
filter_size (int|tuple|None): The filter size. If filter_size is a tuple, filter_size (int or tuple): The filter size. If filter_size is a tuple,
it must contain two integers, (filter_size_H, filter_size_W). it must contain two integers, (filter_size_H, filter_size_W).
Otherwise, the filter will be a square. Otherwise, the filter will be a square.
stride (int|tuple): The stride size. If stride is a tuple, it must stride (int or tuple, optional): The stride size. If stride is a tuple, it must
contain two integers, (stride_H, stride_W). Otherwise, the contain two integers, (stride_H, stride_W). Otherwise, the
stride_H = stride_W = stride. Default: stride = 1. stride_H = stride_W = stride. Default: 1.
padding (int|tuple): The padding size. If padding is a tuple, it must padding (int or tuple, optional): The padding size. If padding is a tuple, it must
contain two integers, (padding_H, padding_W). Otherwise, the contain two integers, (padding_H, padding_W). Otherwise, the
padding_H = padding_W = padding. Default: padding = 0. padding_H = padding_W = padding. Default: 0.
dilation (int|tuple): The dilation size. If dilation is a tuple, it must dilation (int or tuple, optional): The dilation size. If dilation is a tuple, it must
contain two integers, (dilation_H, dilation_W). Otherwise, the contain two integers, (dilation_H, dilation_W). Otherwise, the
dilation_H = dilation_W = dilation. Default: dilation = 1. dilation_H = dilation_W = dilation. Default: 1.
groups (int): The groups number of the Conv2d Layer. According to grouped groups (int, optional): The groups number of the Conv2d Layer. According to grouped
convolution in Alex Krizhevsky's Deep CNN paper: when group=2, convolution in Alex Krizhevsky's Deep CNN paper: when group=2,
the first half of the filters is only connected to the first half the first half of the filters is only connected to the first half
of the input channels, while the second half of the filters is only of the input channels, while the second half of the filters is only
connected to the second half of the input channels. Default: groups=1. connected to the second half of the input channels. Default: 1.
param_attr (ParamAttr|None): The parameter attribute for learnable parameters/weights param_attr (ParamAttr, optional): The parameter attribute for learnable weights(Parameter)
of conv2d. If it is set to None or one attribute of ParamAttr, conv2d of conv2d. If it is set to None or one attribute of ParamAttr, conv2d
will create ParamAttr as param_attr. If the Initializer of the param_attr will create ParamAttr as param_attr. If the Initializer of the param_attr
is not set, the parameter is initialized with :math:`Normal(0.0, std)`, is not set, the parameter is initialized with :math:`Normal(0.0, std)`,
and the :math:`std` is :math:`(\\frac{2.0 }{filter\_elem\_num})^{0.5}`. Default: None. and the :math:`std` is :math:`(\\frac{2.0 }{filter\_elem\_num})^{0.5}`. Default: None.
bias_attr (ParamAttr|bool|None): The parameter attribute for the bias of conv2d. bias_attr (ParamAttr or bool, optional): The attribute for the bias of conv2d.
If it is set to False, no bias will be added to the output units. If it is set to False, no bias will be added to the output units.
If it is set to None or one attribute of ParamAttr, conv2d If it is set to None or one attribute of ParamAttr, conv2d
will create ParamAttr as bias_attr. If the Initializer of the bias_attr will create ParamAttr as bias_attr. If the Initializer of the bias_attr
is not set, the bias is initialized zero. Default: None. is not set, the bias is initialized zero. Default: None.
use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn use_cudnn (bool, optional): Use cudnn kernel or not, it is valid only when the cudnn
library is installed. Default: True library is installed. Default: True.
act (str): Activation type, if it is set to None, activation is not appended. act (str, optional): Activation type, if it is set to None, activation is not appended.
Default: None Default: None.
dtype (str, optional): Data type, it can be "float32" or "float64". Default: "float32".
Attributes: Attribute:
weight (Parameter): the learnable weights of filter of this layer. **weight** (Parameter): the learnable weights of filter of this layer.
bias (Parameter|None): the learnable bias of this layer.
**bias** (Parameter or None): the learnable bias of this layer.
Returns:
None
Raises: Raises:
ValueError: If the shapes of input, filter_size, stride, padding and ValueError: if ``use_cudnn`` is not a bool value.
groups mismatch.
Examples: Examples:
.. code-block:: python .. code-block:: python
...@@ -135,11 +141,11 @@ class Conv2D(layers.Layer): ...@@ -135,11 +141,11 @@ class Conv2D(layers.Layer):
from paddle.fluid.dygraph import Conv2D from paddle.fluid.dygraph import Conv2D
import numpy as np import numpy as np
data = np.random.uniform( -1, 1, [10, 3, 32, 32] ).astype('float32') data = np.random.uniform(-1, 1, [10, 3, 32, 32]).astype('float32')
with fluid.dygraph.guard(): with fluid.dygraph.guard():
conv2d = Conv2D( "conv2d", 2, 3) conv2d = Conv2D("conv2d", 2, 3)
data = to_variable( data ) data = to_variable(data)
conv = conv2d( data ) conv = conv2d(data)
""" """
...@@ -723,33 +729,82 @@ class Conv3DTranspose(layers.Layer): ...@@ -723,33 +729,82 @@ class Conv3DTranspose(layers.Layer):
class Pool2D(layers.Layer): class Pool2D(layers.Layer):
""" """
The pooling2d operation calculates the output based on the input, pooling_type and ksize, strides, This interface is used to construct a callable object of the ``Pool2D`` class.
paddings parameters.Input(X) and output(Out) are in NCHW format, where N is batch size, C is the number of channels, For more details, refer to code examples.
H is the height of the feature, and W is the width of the feature. The pooling2d operation calculates the output based on the input, pool_type and pool_size, pool_stride,
pool_padding parameters.Input and output are in NCHW format, where N is batch size, C is the number of feature map,
H is the height of the feature map, and W is the width of the feature map.
Parameters(ksize, strides, paddings) are two elements. These two elements represent height and width, respectively. Parameters(ksize, strides, paddings) are two elements. These two elements represent height and width, respectively.
The input(X) size and output(Out) size may be different. The input(X) size and output(Out) size may be different.
Example:
- Input:
Input shape: :math:`(N, C, H_{in}, W_{in})`
- Output:
Output shape: :math:`(N, C, H_{out}, W_{out})`
If ``ceil_mode`` = False:
.. math::
H_{out} = \\frac{(H_{in} - ksize[0] + 2 * paddings[0])}{strides[0]} + 1 \\\\
W_{out} = \\frac{(W_{in} - ksize[1] + 2 * paddings[1])}{strides[1]} + 1
If ``ceil_mode`` = True:
.. math::
H_{out} = \\frac{(H_{in} - ksize[0] + 2 * paddings[0] + strides[0] - 1)}{strides[0]} + 1 \\\\
W_{out} = \\frac{(W_{in} - ksize[1] + 2 * paddings[1] + strides[1] - 1)}{strides[1]} + 1
If ``exclusive`` = False:
.. math::
hstart &= i * strides[0] - paddings[0] \\\\
hend &= hstart + ksize[0] \\\\
wstart &= j * strides[1] - paddings[1] \\\\
wend &= wstart + ksize[1] \\\\
Output(i ,j) &= \\frac{sum(Input[hstart:hend, wstart:wend])}{ksize[0] * ksize[1]}
If ``exclusive`` = True:
.. math::
hstart &= max(0, i * strides[0] - paddings[0])\\\\
hend &= min(H, hstart + ksize[0]) \\\\
wstart &= max(0, j * strides[1] - paddings[1]) \\\\
wend & = min(W, wstart + ksize[1]) \\\\
Output(i ,j) & = \\frac{sum(Input[hstart:hend, wstart:wend])}{(hend - hstart) * (wend - wstart)}
Parameters: Parameters:
name_scope(str) : The name of this class. name_scope(str) : The name of this class.
pool_size (int|list|tuple): The pool kernel size. If pool kernel size is a tuple or list, pool_size (int or list or tuple, optional): The pool kernel size. If pool kernel size is a tuple or list,
it must contain two integers, (pool_size_Height, pool_size_Width). it must contain two integers, (pool_size_Height, pool_size_Width).
Otherwise, the pool kernel size will be a square of an int. Default: -1 Otherwise, the pool kernel size will be a square of an int. Default: -1.
pool_type(str) : The pooling type, can be "max" for max-pooling and "avg" for average-pooling. Default: max pool_type(str, optional) : The pooling type, can be "max" for max-pooling and "avg" for average-pooling.
pool_stride (int|list|tuple): The pool stride size. If pool stride size is a tuple or list, Default: max.
pool_stride (int or list or tuple, optional): The pool stride size. If pool stride size is a tuple or list,
it must contain two integers, (pool_stride_Height, pool_stride_Width). Otherwise, it must contain two integers, (pool_stride_Height, pool_stride_Width). Otherwise,
the pool stride size will be a square of an int. Default: 1 the pool stride size will be a square of an int. Default: 1.
pool_padding (int|list|tuple): The pool padding size. If pool padding size is a tuple, pool_padding (int or list or tuple, optional): The padding size for pooling operation.
If ``pool_padding`` is a tuple,
it must contain two integers, (pool_padding_on_Height, pool_padding_on_Width). it must contain two integers, (pool_padding_on_Height, pool_padding_on_Width).
Otherwise, the pool padding size will be a square of an int. Default: 0 Otherwise, the padding size for pooling operation will be a square of an int. Default: 0.
global_pooling (bool): Whether to use the global pooling. If global_pooling = true, global_pooling (bool, optional): Whether to use the global pooling. If global_pooling = true,
kernel size and paddings will be ignored. Default: False kernel size and paddings will be ignored. Default: False.
use_cudnn (bool): Only used in cudnn kernel, need install cudnn. Default: True use_cudnn (bool, optional): Only used in cudnn kernel, need install cudnn. Default: True.
ceil_mode (bool): Whether to use the ceil function to calculate output height and width. ceil_mode (bool, optional): Whether to use the ceil function to calculate output height and width.
False is the default. If it is set to False, the floor function will be used. Default: False False is the default. If it is set to False, the floor function will be used. Default: False.
exclusive (bool): Whether to exclude padding points in average pooling mode. Default: True exclusive (bool, optional): Whether to exclude padding points in average pooling mode. Default: True.
dtype (str, optional): Data type, it can be "float32" or "float64". Default: "float32".
Returns: Returns:
Variable: The pooling result. None
Raises: Raises:
ValueError: If 'pool_type' is not "max" nor "avg" ValueError: If 'pool_type' is not "max" nor "avg"
...@@ -761,16 +816,16 @@ class Pool2D(layers.Layer): ...@@ -761,16 +816,16 @@ class Pool2D(layers.Layer):
.. code-block:: python .. code-block:: python
import paddle.fluid as fluid import paddle.fluid as fluid
import numpy from paddle.fluid.dygraph.base import to_variable
import numpy as np
with fluid.dygraph.guard(): with fluid.dygraph.guard():
data = numpy.random.random((3, 32, 32)).astype('float32') data = numpy.random.random((3, 32, 32, 5)).astype('float32')
pool2d = fluid.dygraph.Pool2D("pool2d",pool_size=2, pool2d = fluid.dygraph.Pool2D("pool2d",pool_size=2,
pool_type='max', pool_type='max',
pool_stride=1, pool_stride=1,
global_pooling=False) global_pooling=False)
pool2d_res = pool2d(data) pool2d_res = pool2d(to_variable(data))
""" """
...@@ -834,26 +889,25 @@ class Pool2D(layers.Layer): ...@@ -834,26 +889,25 @@ class Pool2D(layers.Layer):
class FC(layers.Layer): class FC(layers.Layer):
""" """
**Fully Connected Layer** This interface is used to construct a callable object of the ``FC`` class.
For more details, refer to code examples.
This function creates a fully connected layer in the network. It can take It creates a fully connected layer in the network. It can take
one or multiple tensors as its inputs(input can be a list of Variable, see one or multiple ``Tensor`` as its inputs. It creates a Variable called weights for each input tensor,
Args in detail). It creates a variable called weights for each input tensor,
which represents a fully connected weight matrix from each input unit to which represents a fully connected weight matrix from each input unit to
each output unit. The fully connected layer multiplies each input tensor each output unit. The fully connected layer multiplies each input tensor
with its corresponding weight to produce an output Tensor with shape [M, `size`], with its corresponding weight to produce an output Tensor with shape [N, `size`],
where M is batch size. If multiple input tensors are given, the results of where N is batch size. If multiple input tensors are given, the results of
multiple output tensors with shape [M, `size`] will be summed up. If bias_attr multiple output tensors with shape [N, `size`] will be summed up. If ``bias_attr``
is not None, a bias variable will be created and added to the output. is not None, a bias variable will be created and added to the output.
Finally, if activation is not None, it will be applied to the output as well. Finally, if ``act`` is not None, it will be applied to the output as well.
When the input is single tensor: When the input is single ``Tensor`` :
.. math:: .. math::
Out = Act({XW + b}) Out = Act({XW + b})
When the input are multiple tensors: When the input are multiple ``Tensor`` :
.. math:: .. math::
...@@ -861,36 +915,36 @@ class FC(layers.Layer): ...@@ -861,36 +915,36 @@ class FC(layers.Layer):
In the above equation: In the above equation:
* :math:`N`: Number of the input. N equals to len(input) if input is list of Variable. * :math:`N`: Number of the input. N equals to len(input) if input is list of ``Tensor`` .
* :math:`X_i`: The i-th input tensor. * :math:`X_i`: The i-th input ``Tensor`` .
* :math:`W_i`: The i-th weights matrix corresponding i-th input tensor. * :math:`W_i`: The i-th weights matrix corresponding i-th input tensor.
* :math:`b`: The bias parameter created by this layer (if needed). * :math:`b`: The bias parameter created by this layer (if needed).
* :math:`Act`: The activation function. * :math:`Act`: The activation function.
* :math:`Out`: The output tensor. * :math:`Out`: The output ``Tensor`` .
See below for an example. See below for an example.
.. code-block:: text .. code-block:: text
Given: Given:
data_1.data = [[[0.1, 0.2], data_1.data = [[[0.1, 0.2]]]
[0.3, 0.4]]] data_1.shape = (1, 1, 2) # 1 is batch_size
data_1.shape = (1, 2, 2) # 1 is batch_size
data_2 = [[[0.1, 0.2, 0.3]]] data_2.data = [[[0.1, 0.2, 0.3]]]
data_2.shape = (1, 1, 3) data_2.shape = (1, 1, 3) # 1 is batch_size
out = fluid.layers.fc(input=[data_1, data_2], size=2) fc = FC("fc", 2, num_flatten_dims=2)
out = fc(input=[data_1, data_2])
Then: Then:
out.data = [[0.18669507, 0.1893476]] out.data = [[[0.182996 -0.474117]]]
out.shape = (1, 2) out.shape = (1, 1, 2)
Parameters: Parameters:
name_scope(str): The name of this class. name_scope(str): The name of this class.
size(int): The number of output units in this layer. size(int): The number of output units in this layer.
num_flatten_dims (int): The fc layer can accept an input tensor with more than num_flatten_dims (int, optional): The fc layer can accept an input tensor with more than
two dimensions. If this happens, the multidimensional tensor will first be flattened two dimensions. If this happens, the multi-dimension tensor will first be flattened
into a 2-dimensional matrix. The parameter `num_flatten_dims` determines how the input into a 2-dimensional matrix. The parameter `num_flatten_dims` determines how the input
tensor is flattened: the first `num_flatten_dims` (inclusive, index starts from 1) tensor is flattened: the first `num_flatten_dims` (inclusive, index starts from 1)
dimensions will be flatten to form the first dimension of the final matrix (height of dimensions will be flatten to form the first dimension of the final matrix (height of
...@@ -898,22 +952,23 @@ class FC(layers.Layer): ...@@ -898,22 +952,23 @@ class FC(layers.Layer):
form the second dimension of the final matrix (width of the matrix). For example, suppose form the second dimension of the final matrix (width of the matrix). For example, suppose
`X` is a 5-dimensional tensor with a shape [2, 3, 4, 5, 6], and `num_flatten_dims` = 3. `X` is a 5-dimensional tensor with a shape [2, 3, 4, 5, 6], and `num_flatten_dims` = 3.
Then, the flattened matrix will have a shape [2 x 3 x 4, 5 x 6] = [24, 30]. Default: 1 Then, the flattened matrix will have a shape [2 x 3 x 4, 5 x 6] = [24, 30]. Default: 1
param_attr (ParamAttr|list of ParamAttr|None): The parameter attribute for learnable param_attr (ParamAttr or list of ParamAttr, optional): The parameter attribute for learnable
parameters/weights of this layer. weights(Parameter) of this layer. Default: None.
bias_attr (ParamAttr|list of ParamAttr, default None): The parameter attribute for the bias bias_attr (ParamAttr or list of ParamAttr, optional): The attribute for the bias
of this layer. If it is set to False, no bias will be added to the output units. of this layer. If it is set to False, no bias will be added to the output units.
If it is set to None, the bias is initialized zero. Default: None. If it is set to None, the bias is initialized zero. Default: None.
act (str|None): Activation to be applied to the output of this layer. act (str, optional): Activation to be applied to the output of this layer. Default: None.
is_test(bool): A flag indicating whether execution is in test phase. Default: False is_test(bool, optional): A flag indicating whether execution is in test phase. Default: False.
dtype(str): Dtype used for weight dtype(str, optional): Dtype used for weight, it can be "float32" or "float64". Default: "float32".
Attributes: Attribute:
weight (list of Parameter): the learnable weights of this layer. **weight** (list of Parameter): the learnable weights of this layer.
bias (Parameter|None): the learnable bias of this layer.
Raises: **bias** (Parameter or None): the learnable bias of this layer.
ValueError: If rank of the input tensor is less than 2.
Returns:
None
Examples: Examples:
.. code-block:: python .. code-block:: python
...@@ -922,11 +977,11 @@ class FC(layers.Layer): ...@@ -922,11 +977,11 @@ class FC(layers.Layer):
from paddle.fluid.dygraph import FC from paddle.fluid.dygraph import FC
import numpy as np import numpy as np
data = np.random.uniform( -1, 1, [30, 10, 32] ).astype('float32') data = np.random.uniform(-1, 1, [30, 10, 32]).astype('float32')
with fluid.dygraph.guard(): with fluid.dygraph.guard():
fc = FC( "fc", 64, num_flatten_dims=2) fc = FC("fc", 64, num_flatten_dims=2)
data = to_variable( data ) data = to_variable(data)
conv = fc( data ) conv = fc(data)
""" """
...@@ -2137,19 +2192,21 @@ class BilinearTensorProduct(layers.Layer): ...@@ -2137,19 +2192,21 @@ class BilinearTensorProduct(layers.Layer):
class Conv2DTranspose(layers.Layer): class Conv2DTranspose(layers.Layer):
""" """
**Convlution2D transpose layer** This interface is used to construct a callable object of the ``Conv2DTranspose`` class.
For more details, refer to code examples.
The convolution2D transpose layer calculates the output based on the input, The convolution2D transpose layer calculates the output based on the input,
filter, and dilations, strides, paddings. Input(Input) and output(Output) filter, and dilations, strides, paddings. Input and output
are in NCHW format. Where N is batch size, C is the number of channels, are in NCHW format. Where N is batch size, C is the number of feature map,
H is the height of the feature, and W is the width of the feature. H is the height of the feature map, and W is the width of the feature map.
Parameters(dilations, strides, paddings) are two elements. These two elements Filter's shape is [MCHW] , where M is the number of output feature map,
represent height and width, respectively. The details of convolution transpose C is the number of input feature map, H is the height of the filter,
layer, please refer to the following explanation and references and W is the width of the filter. If the groups is greater than 1,
`therein <http://www.matthewzeiler.com/wp-content/uploads/2017/07/cvpr2010.pdf>`_. C will equal the number of input feature map divided by the groups.
If bias attribution and activation type are provided, bias is added to If bias attribution and activation type are provided, bias is added to
the output of the convolution, and the corresponding activation function the output of the convolution, and the corresponding activation function
is applied to the final result. is applied to the final result.
The details of convolution transpose layer, please refer to the following explanation and references
`conv2dtranspose <http://www.matthewzeiler.com/wp-content/uploads/2017/07/cvpr2010.pdf>`_ .
For each input :math:`X`, the equation is: For each input :math:`X`, the equation is:
...@@ -2159,10 +2216,10 @@ class Conv2DTranspose(layers.Layer): ...@@ -2159,10 +2216,10 @@ class Conv2DTranspose(layers.Layer):
Where: Where:
* :math:`X`: Input value, a tensor with NCHW format. * :math:`X`: Input value, a ``Tensor`` with NCHW format.
* :math:`W`: Filter value, a tensor with MCHW format. * :math:`W`: Filter value, a ``Tensor`` with shape [MCHW] .
* :math:`\\ast`: Convolution operation. * :math:`\\ast`: Convolution operation.
* :math:`b`: Bias value, a 2-D tensor with shape [M, 1]. * :math:`b`: Bias value, a 2-D ``Tensor`` with shape [M, 1].
* :math:`\\sigma`: Activation function. * :math:`\\sigma`: Activation function.
* :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different. * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different.
...@@ -2190,64 +2247,61 @@ class Conv2DTranspose(layers.Layer): ...@@ -2190,64 +2247,61 @@ class Conv2DTranspose(layers.Layer):
Parameters: Parameters:
name_scope(str): The name of this class. name_scope(str): The name of this class.
num_filters(int): The number of the filter. It is as same as the output num_filters(int): The number of the filter. It is as same as the output
image channel. feature map.
output_size(int|tuple|None): The output image size. If output size is a output_size(int or tuple, optional): The output image size. If output size is a
tuple, it must contain two integers, (image_H, image_W). None if use tuple, it must contain two integers, (image_H, image_W). None if use
filter_size, padding, and stride to calculate output_size. filter_size, padding, and stride to calculate output_size.
if output_size and filter_size are specified at the same time, They if output_size and filter_size are specified at the same time, They
should follow the formula above. Default: None. should follow the formula above. Default: None.
filter_size(int|tuple|None): The filter size. If filter_size is a tuple, filter_size(int or tuple, optional): The filter size. If filter_size is a tuple,
it must contain two integers, (filter_size_H, filter_size_W). it must contain two integers, (filter_size_H, filter_size_W).
Otherwise, the filter will be a square. None if use output size to Otherwise, the filter will be a square. None if use output size to
calculate filter_size. Default: None. calculate filter_size. Default: None.
padding(int|tuple): The padding size. If padding is a tuple, it must padding(int or tuple, optional): The padding size. If padding is a tuple, it must
contain two integers, (padding_H, padding_W). Otherwise, the contain two integers, (padding_H, padding_W). Otherwise, the
padding_H = padding_W = padding. Default: padding = 0. padding_H = padding_W = padding. Default: 0.
stride(int|tuple): The stride size. If stride is a tuple, it must stride(int or tuple, optional): The stride size. If stride is a tuple, it must
contain two integers, (stride_H, stride_W). Otherwise, the contain two integers, (stride_H, stride_W). Otherwise, the
stride_H = stride_W = stride. Default: stride = 1. stride_H = stride_W = stride. Default: 1.
dilation(int|tuple): The dilation size. If dilation is a tuple, it must dilation(int or tuple, optional): The dilation size. If dilation is a tuple, it must
contain two integers, (dilation_H, dilation_W). Otherwise, the contain two integers, (dilation_H, dilation_W). Otherwise, the
dilation_H = dilation_W = dilation. Default: dilation = 1. dilation_H = dilation_W = dilation. Default: 1.
groups(int): The groups number of the Conv2d transpose layer. Inspired by groups(int, optional): The groups number of the Conv2d transpose layer. Inspired by
grouped convolution in Alex Krizhevsky's Deep CNN paper, in which grouped convolution in Alex Krizhevsky's Deep CNN paper, in which
when group=2, the first half of the filters is only connected to the when group=2, the first half of the filters is only connected to the
first half of the input channels, while the second half of the first half of the input channels, while the second half of the
filters is only connected to the second half of the input channels. filters is only connected to the second half of the input channels.
Default: groups = 1. Default: 1.
param_attr (ParamAttr|None): The parameter attribute for learnable parameters/weights param_attr (ParamAttr, optional): The parameter attribute for learnable weights(Parameter)
of conv2d_transpose. If it is set to None or one attribute of ParamAttr, conv2d_transpose of conv2d_transpose. If it is set to None or one attribute of ParamAttr, conv2d_transpose
will create ParamAttr as param_attr. If the Initializer of the param_attr will create ParamAttr as param_attr. If the Initializer of the param_attr
is not set, the parameter is initialized with Xavier. Default: None. is not set, the parameter is initialized with Xavier. Default: None.
bias_attr (ParamAttr|bool|None): The parameter attribute for the bias of conv2d_transpose. bias_attr (ParamAttr or bool, optional): The attribute for the bias of conv2d_transpose.
If it is set to False, no bias will be added to the output units. If it is set to False, no bias will be added to the output units.
If it is set to None or one attribute of ParamAttr, conv2d_transpose If it is set to None or one attribute of ParamAttr, conv2d_transpose
will create ParamAttr as bias_attr. If the Initializer of the bias_attr will create ParamAttr as bias_attr. If the Initializer of the bias_attr
is not set, the bias is initialized zero. Default: None. is not set, the bias is initialized zero. Default: None.
use_cudnn(bool): Use cudnn kernel or not, it is valid only when the cudnn use_cudnn(bool, optional): Use cudnn kernel or not, it is valid only when the cudnn
library is installed. Default: True. library is installed. Default: True.
act (str): Activation type, if it is set to None, activation is not appended. act (str, optional): Activation type, if it is set to None, activation is not appended.
Default: None. Default: None.
Attributes: Attribute:
weight (Parameter): the learnable weights of filters of this layer. **weight** (Parameter): the learnable weights of filters of this layer.
bias (Parameter|None): the learnable bias of this layer.
Returns: **bias** (Parameter or None): the learnable bias of this layer.
Variable: The tensor variable storing the convolution transpose result.
Raises: Returns:
ValueError: If the shapes of input, filter_size, stride, padding and None
groups mismatch.
Examples: Examples:
.. code-block:: python .. code-block:: python
import paddle.fluid as fluid import paddle.fluid as fluid
import numpy import numpy as np
with fluid.dygraph.guard(): with fluid.dygraph.guard():
data = numpy.random.random((3, 32, 32)).astype('float32') data = np.random.random((3, 32, 32, 5)).astype('float32')
conv2DTranspose = fluid.dygraph.nn.Conv2DTranspose( conv2DTranspose = fluid.dygraph.nn.Conv2DTranspose(
'Conv2DTranspose', num_filters=2, filter_size=3) 'Conv2DTranspose', num_filters=2, filter_size=3)
ret = conv2DTranspose(fluid.dygraph.base.to_variable(data)) ret = conv2DTranspose(fluid.dygraph.base.to_variable(data))
...@@ -2765,47 +2819,46 @@ class SpectralNorm(layers.Layer): ...@@ -2765,47 +2819,46 @@ class SpectralNorm(layers.Layer):
class TreeConv(layers.Layer): class TreeConv(layers.Layer):
""" """
***Tree-Based Convolution Operator*** This interface is used to construct a callable object of the ``TreeConv`` class.
For more details, refer to code examples.
Tree-Based Convolution is a kind of convolution based on tree structure. Tree-Based Convolution is a kind of convolution based on tree structure.
Tree-Based Convolution is a part of Tree-Based Convolution Neural Network(TBCNN), Tree-Based Convolution is a part of Tree-Based Convolution Neural Network(TBCNN),
which is used to classify tree structures, such as Abstract Syntax Tree. which is used to classify tree structures, such as Abstract Syntax Tree.
Tree-Based Convolution proposed a kind of data structure called continuous binary tree, Tree-Based Convolution proposed a kind of data structure called continuous binary tree,
which regards multiway tree as binary tree. which regards multiway tree as binary tree.
The paper of Tree-Based Convolution Operator is here: https://arxiv.org/abs/1409.5718v1 The paper of Tree-Based Convolution Operator is here: `tree-based convolution <https://arxiv.org/abs/1409.5718v1/>`_ .
Parameters:
Parameters: name_scope(str): The name of this class.
name_scope(str): The name of this class. output_size(int): output feature width.
output_size(int): output feature width num_filters(int, optional): number of filters, Default: 1.
num_filters(int): number of filters, Default: 1. max_depth(int, optional): max depth of filters, Default: 2.
max_depth(int): max depth of filters, Default: 2. act(str, optional): activation function, Default: tanh.
act(str): activation function, Default: tanh. param_attr(ParamAttr, optional): the parameter attribute for the filters, Default: None.
param_attr(ParamAttr): the parameter attribute for the filters, Default: None. bias_attr(ParamAttr, optional): the parameter attribute for the bias of this layer, Default: None.
bias_attr(ParamAttr): the parameter attribute for the bias of this layer, Default: None. name(str, optional): The default value is None. Normally there is no need for user to set this property. For more information, please refer to :ref:`api_guide_Name` .
name(str): a name of this layer(optional). If set None, the layer will be named automatically, Default: None.
Attributes: Attribute:
weight (Parameter): the learnable weights of filters of this layer. **weight** (Parameter): the learnable weights of filters of this layer.
bias (Parameter|None): the learnable bias of this layer.
Returns: **bias** (Parameter or None): the learnable bias of this layer.
out(Variable): (Tensor) The feature vector of subtrees. The shape of the output tensor is [max_tree_node_size, output_size, num_filters]. The output tensor could be a new feature vector for next tree convolution layers
Examples: Returns:
None
.. code-block:: python Examples:
import paddle.fluid as fluid .. code-block:: python
import numpy
with fluid.dygraph.guard(): import paddle.fluid as fluid
nodes_vector = numpy.random.random((1, 10, 5)).astype('float32') import numpy
edge_set = numpy.random.random((1, 9, 2)).astype('int32')
treeConv = fluid.dygraph.nn.TreeConv(
'TreeConv', output_size=6, num_filters=1, max_depth=2)
ret = treeConv(fluid.dygraph.base.to_variable(nodes_vector), fluid.dygraph.base.to_variable(edge_set))
with fluid.dygraph.guard():
nodes_vector = numpy.random.random((1, 10, 5)).astype('float32')
edge_set = numpy.random.random((1, 9, 2)).astype('int32')
treeConv = fluid.dygraph.nn.TreeConv(
'TreeConv', output_size=6, num_filters=1, max_depth=2)
ret = treeConv(fluid.dygraph.base.to_variable(nodes_vector), fluid.dygraph.base.to_variable(edge_set))
""" """
def __init__(self, def __init__(self,
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或