The API will create a ``Variable`` object from numpy\.ndarray or Variable object.
Args:
Parameters:
value(ndarray): the numpy value need to be convert
value(ndarray): The numpy\.ndarray object that needs to be converted, it can be multi-dimension, and the data type is one of numpy\.{float16, float32, float64, int16, int32, int64, uint8, uint16}.
block(fluid.Block|None): which block this variable will be in
block(fluid.Block, optional): Which block this variable will be in. Default: None.
name(str|None): Name of Variable
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`
return:
Returns:
Variable: The variable created from given numpy
Variable: ``Tensor`` created from the specified numpy\.ndarray object, data type and shape is the same as ``value`` .
@@ -1683,39 +1800,43 @@ class GRUUnit(layers.Layer):
...
@@ -1683,39 +1800,43 @@ class GRUUnit(layers.Layer):
classNCE(layers.Layer):
classNCE(layers.Layer):
"""
"""
Compute and return the noise-contrastive estimation training loss. See
This interface is used to construct a callable object of the ``NCE`` class.
For more details, refer to code examples.
It implements the function of the ``NCE`` loss function.
By default this function uses a uniform distribution for sampling, and it
compute and return the noise-contrastive estimation training loss. See
`Noise-contrastive estimation: A new estimation principle for unnormalized statistical models <http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf>`_ .
`Noise-contrastive estimation: A new estimation principle for unnormalized statistical models <http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf>`_ .
By default this operator uses a uniform distribution for sampling.
Parameters:
Parameters:
name_scope(str): The name of this class.
name_scope(str): The name of this class.
num_total_classes (int): Total number of classes in all samples
num_total_classes (int): Total number of classes in all samples
param_attr (ParamAttr|None): The parameter attribute for learnable parameters/weights
param_attr (ParamAttr, optional): The parameter attribute for learnable weights(Parameter)
of nce. If it is set to None or one attribute of ParamAttr, nce
of nce. If it is set to None or one attribute of ParamAttr, nce
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 nce.
bias_attr (ParamAttr or bool, optional): The attribute for the bias of nce.
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, nce
If it is set to None or one attribute of ParamAttr, nce
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.
num_neg_samples (int): The number of negative classes. The default value is 10.
num_neg_samples (int, optional): The number of negative classes. The default value is 10.
sampler (str): The sampler used to sample class from negtive classes.
sampler (str, optional): The sampler used to sample class from negtive classes.
It can be 'uniform', 'log_uniform' or 'custom_dist'.
It can be 'uniform', 'log_uniform' or 'custom_dist'.
default: 'uniform'.
default: 'uniform'.
custom_dist (float[]|None): A float[] with size=num_total_classes.
custom_dist (float[], optional): A float[] with size=num_total_classes.
It is used when sampler is set to 'custom_dist'.
It is used when sampler is set to 'custom_dist'.
custom_dist[i] is the probability of i-th class to be sampled.
custom_dist[i] is the probability of i-th class to be sampled.
Default: None.
Default: None.
seed (int): The seed used in sampler. Default: 0.
seed (int, optional): The seed used in sampler. Default: 0.
is_sparse(bool): The flag indicating whether to use sparse update, the weight@GRAD and bias@GRAD will be changed to SelectedRows. Default: False.
is_sparse(bool, optional): The flag indicating whether to use sparse update. If is_sparse is True, the weight@GRAD and bias@GRAD will be changed to SelectedRows. Default: False.
Attributes:
Attribute:
weight (Parameter): the learnable weights of this layer.
**weight** (Parameter): the learnable weights of this layer.
bias (Parameter|None): the learnable bias of this layer.
**bias** (Parameter or None): the learnable bias of this layer.
Returns:
Returns:
Variable: The output nce loss.
None
Examples:
Examples:
.. code-block:: python
.. code-block:: python
...
@@ -1932,6 +2053,10 @@ class NCE(layers.Layer):
...
@@ -1932,6 +2053,10 @@ class NCE(layers.Layer):
classPRelu(layers.Layer):
classPRelu(layers.Layer):
"""
"""
This interface is used to construct a callable object of the ``PRelu`` class.
For more details, refer to code examples.
It implements three activation methods of the ``PRelu`` activation function.
Equation:
Equation:
.. math::
.. math::
...
@@ -1943,30 +2068,32 @@ class PRelu(layers.Layer):
...
@@ -1943,30 +2068,32 @@ class PRelu(layers.Layer):
and element. all: all elements share same weight
and element. all: all elements share same weight
channel:elements in a channel share same weight
channel:elements in a channel share same weight
element:each element has a weight
element:each element has a weight
param_attr(ParamAttr|None): The parameter attribute for the learnable
param_attr(ParamAttr, optional): The parameter attribute for the learnable
weight (alpha).
weight (alpha). Default: None.
Attributes:
Attribute:
weight (Parameter): the learnable weights of this layer.
**weight** (Parameter): the learnable weights of this layer.
Returns:
Returns:
Variable: The output tensor with the same shape as input.
ret = groupNorm(fluid.dygraph.base.to_variable(x))
ret = groupNorm(fluid.dygraph.base.to_variable(x))
...
@@ -2661,8 +2788,8 @@ class GroupNorm(layers.Layer):
...
@@ -2661,8 +2788,8 @@ class GroupNorm(layers.Layer):
classSpectralNorm(layers.Layer):
classSpectralNorm(layers.Layer):
"""
"""
**Spectral Normalization Layer**
This interface is used to construct a callable object of the ``SpectralNorm`` class.
For more details, refer to code examples. It implements the function of the Spectral Normalization Layer.
This layer calculates the spectral normalization value of weight parameters of
This layer calculates the spectral normalization value of weight parameters of
fc, conv1d, conv2d, conv3d layers which should be 2-D, 3-D, 4-D, 5-D
fc, conv1d, conv2d, conv3d layers which should be 2-D, 3-D, 4-D, 5-D
Parameters. Calculations are showed as follows.
Parameters. Calculations are showed as follows.
...
@@ -2696,22 +2823,22 @@ class SpectralNorm(layers.Layer):
...
@@ -2696,22 +2823,22 @@ class SpectralNorm(layers.Layer):
Parameters:
Parameters:
name_scope(str): The name of this class.
name_scope(str): The name of this class.
dim(int): The index of dimension which should be permuted to the first before reshaping Input(Weight) to matrix, it should be set as 0 if Input(Weight) is the weight of fc layer, and should be set as 1 if Input(Weight) is the weight of conv layer. Default: 0.
dim(int, optional): The index of dimension which should be permuted to the first before reshaping Input(Weight) to matrix, it should be set as 0 if Input(Weight) is the weight of fc layer, and should be set as 1 if Input(Weight) is the weight of conv layer. Default: 0.
power_iters(int): The number of power iterations to calculate spectral norm. Default: 1.
power_iters(int, optional): The number of power iterations to calculate spectral norm. Default: 1.
eps(float): The epsilon for numerical stability in calculating norms. Default: 1e-12.
eps(float, optional): The epsilon for numerical stability in calculating norms. Default: 1e-12.
name (str): The name of this layer. It is optional.
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` .
Returns:
Returns:
Variable: A tensor variable of weight parameters after spectral normalization.
None
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():
x = numpy.random.random((2, 8, 32, 32)).astype('float32')
x = np.random.random((2, 8, 32, 32)).astype('float32')
param_attr(ParamAttr): the parameter attribute for the filters, Default: None.
param_attr(ParamAttr, optional): the parameter attribute for the filters, Default: None.
bias_attr(ParamAttr): the parameter attribute for the bias of this layer, Default: None.
bias_attr(ParamAttr, optional): the parameter attribute for the bias of this layer, Default: None.
name(str): a name of this layer(optional). If set None, the layer will be named automatically, 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` .
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.
**bias** (Parameter or None): the learnable bias of this layer.
Returns:
Returns:
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
None
Examples:
Examples:
...
@@ -2801,7 +2928,6 @@ class TreeConv(layers.Layer):
...
@@ -2801,7 +2928,6 @@ class TreeConv(layers.Layer):
input (Variable): The input variable. A LoDTensor or Tensor with type
input (Variable): The input variable. A multi-dimension ``Tensor`` with type float32 or float64.
float32, float64.
use_cudnn (bool, optional): Use cudnn kernel or not, it is valid only when the cudnn \
use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn \
library is installed. To improve numerical stablity, set use_cudnn to \
library is installed. To improve numerical stablity, set use_cudnn to \
False by default. Default: False
False by default.
name (str|None): A name for this layer(optional). If set None, the layer
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` . Default: None.
will be named automatically. Default: None.
will be named automatically. Default: None.
axis (int): The index of dimension to perform softmax calculations, it should
axis (int, optional): The index of dimension to perform softmax calculations, it should
be in range :math:`[-1, rank - 1]`, while :math:`rank` is the rank of
be in range :math:`[-1, rank - 1]`, while :math:`rank` is the rank of
input variable. Default: -1. -1 means the last dimension.
input variable. Default: -1. -1 means the last dimension.
Returns:
Returns:
Variable: output of softmax. A Tensor with type float32, float64.
Variable: ``Tensor`` indicates the output of softmax. The data type and shape are the same as ``input`` .
* :math:`H`: the number of hidden units in a layers
y & = f(\\frac{g}{\\sigma}(x - \\mu) + b)
* :math:`g`: the trainable scale parameter.
- :math:`x`: the vector representation of the summed inputs to the neurons in that layer.
- :math:`H`: the number of hidden units in a layers
* :math:`b`: the trainable bias parameter.
- :math:`\\epsilon`: the small value added to the variance to prevent division by zero.
- :math:`g`: the trainable scale parameter.
- :math:`b`: the trainable bias parameter.
Args:
Args:
input(Variable): The input tensor variable.
input(Variable): A multi-dimension ``Tensor`` , and the data type is float32 or float64.
scale(bool): Whether to learn the adaptive gain :math:`g` after
scale(bool, optional): Whether to learn the adaptive gain :math:`g` after
normalization. Default True.
normalization. Default: True.
shift(bool): Whether to learn the adaptive bias :math:`b` after
shift(bool, optional): Whether to learn the adaptive bias :math:`b` after
normalization. Default True.
normalization. Default: True.
begin_norm_axis(int): The normalization will be performed along
begin_norm_axis(int, optional): The normalization will be performed along
dimensions from :attr:`begin_norm_axis` to :attr:`rank(input)`.
dimensions from :attr:`begin_norm_axis` to :attr:`rank(input)`.
Default 1.
Default: 1.
epsilon(float): The small value added to the variance to prevent
epsilon(float, optional): The small value added to the variance to prevent
division by zero. Default 1e-05.
division by zero. Default: 1e-05.
param_attr(ParamAttr|None): The parameter attribute for the learnable
param_attr(ParamAttr, optional): The parameter attribute for the learnable
gain :math:`g`. If :attr:`scale` is False, :attr:`param_attr` is
gain :math:`g`. If :attr:`scale` is False, :attr:`param_attr` is
omitted. If :attr:`scale` is True and :attr:`param_attr` is None,
omitted. If :attr:`scale` is True and :attr:`param_attr` is None,
a default :code:`ParamAttr` would be added as scale. The
a default :code:`ParamAttr` would be added as scale. The
:attr:`param_attr` is initialized as 1 if it is added. Default None.
:attr:`param_attr` is initialized as 1 if it is added. Default: None.
bias_attr(ParamAttr|None): The parameter attribute for the learnable
bias_attr(ParamAttr, optional): The parameter attribute for the learnable
bias :math:`b`. If :attr:`shift` is False, :attr:`bias_attr` is
bias :math:`b`. If :attr:`shift` is False, :attr:`bias_attr` is
omitted. If :attr:`shift` is True and :attr:`param_attr` is None,
omitted. If :attr:`shift` is True and :attr:`param_attr` is None,
a default :code:`ParamAttr` would be added as bias. The
a default :code:`ParamAttr` would be added as bias. The
:attr:`bias_attr` is initialized as 0 if it is added. Default None.
:attr:`bias_attr` is initialized as 0 if it is added. Default: None.
act(str): Activation to be applied to the output of layer normalizaiton.
act(str, optional): Activation to be applied to the output of layer normalizaiton.
Default None.
Default: None.
name(str): The name of this layer. It is optional. Default None, and a
name(str): 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` .
unique name would be generated automatically.
Returns:
Returns:
${y_comment}
Variable: ``Tensor`` indicating the normalized result, the data type is the same as ``input`` , and the return dimension is the same as ``input`` .
Examples:
Examples:
>>> import paddle.fluid as fluid
.. code-block:: python
>>> data = fluid.layers.data(name='data', shape=[3, 32, 32],
>>> dtype='float32')
import paddle.fluid as fluid
>>> x = fluid.layers.layer_norm(input=data, begin_norm_axis=1)
import numpy as np
x = fluid.data(name='x', shape=[-1, 32, 32], dtype='float32')
Rank loss layer takes batch inputs with size batch_size (batch_size >= 1).
label (Variable): 2-D ``Tensor`` with the shape of :math:`[batch,1]`, the data type is float32, batch indicates the size of the data. Indicats whether A ranked higher than B or not.
left (Variable): 2-D ``Tensor`` with the shape of :math:`[batch,1]`, the data type is float32. RankNet's output score for doc A.
Args:
right (Variable): 2-D ``Tensor`` with the shape of :math:`[batch,1]`, the data type is float32. RankNet's output score for doc B.
label (Variable): Indicats whether A ranked higher than B or not.
name(str|None): 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` .
left (Variable): RankNet's output score for doc A.
right (Variable): RankNet's output score for doc B.
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
Returns:
Returns:
list: The value of rank loss.
Variable: ``Tensor`` indicating the output value of the sort loss layer, the data type is float32, and the return value's shape is :math:`[batch,1]` .
Raises:
Raises:
ValueError: Any of label, left, and right is not a variable.
ValueError: Any of label, left, and right is not a ``Variable`` .
