|
|
|
|
@ -225,11 +225,11 @@ def embedding(input,
|
|
|
|
|
have two elements which indicate the size of the dictionary of
|
|
|
|
|
embeddings and the size of each embedding vector respectively.
|
|
|
|
|
is_sparse(bool): The flag indicating whether to use sparse update.
|
|
|
|
|
is_distributed (bool): Whether to run lookup table from remote parameter server.
|
|
|
|
|
is_distributed(bool): Whether to run lookup table from remote parameter server.
|
|
|
|
|
padding_idx(int|long|None): If :attr:`None`, it makes no effect to lookup.
|
|
|
|
|
Otherwise the given :attr:`padding_idx` indicates padding the output
|
|
|
|
|
with zeros whenever lookup encounters it in :attr:`input`. If
|
|
|
|
|
:math:`padding_idx < 0`, the padding_idx to use in lookup is
|
|
|
|
|
:math:`padding_idx < 0`, the :attr:`padding_idx` to use in lookup is
|
|
|
|
|
:math:`size[0] + dim`.
|
|
|
|
|
param_attr(ParamAttr): Parameters for this layer
|
|
|
|
|
dtype(np.dtype|core.VarDesc.VarType|str): The type of data : float32, float_16, int etc
|
|
|
|
|
@ -364,8 +364,7 @@ def dynamic_lstm(input,
|
|
|
|
|
cell_activation(str): The activation for cell output. Choices = ["sigmoid",
|
|
|
|
|
"tanh", "relu", "identity"], default "tanh".
|
|
|
|
|
candidate_activation(str): The activation for candidate hidden state.
|
|
|
|
|
Choices = ["sigmoid", "tanh",
|
|
|
|
|
"relu", "identity"],
|
|
|
|
|
Choices = ["sigmoid", "tanh", "relu", "identity"],
|
|
|
|
|
default "tanh".
|
|
|
|
|
dtype(str): Data type. Choices = ["float32", "float64"], default "float32".
|
|
|
|
|
name(str|None): A name for this layer(optional). If set None, the layer
|
|
|
|
|
@ -540,27 +539,31 @@ def dynamic_lstmp(input,
|
|
|
|
|
cell_activation(str): The activation for cell output. Choices = ["sigmoid",
|
|
|
|
|
"tanh", "relu", "identity"], default "tanh".
|
|
|
|
|
candidate_activation(str): The activation for candidate hidden state.
|
|
|
|
|
Choices = ["sigmoid", "tanh",
|
|
|
|
|
"relu", "identity"],
|
|
|
|
|
Choices = ["sigmoid", "tanh", "relu", "identity"],
|
|
|
|
|
default "tanh".
|
|
|
|
|
proj_activation(str): The activation for projection output.
|
|
|
|
|
Choices = ["sigmoid", "tanh",
|
|
|
|
|
"relu", "identity"],
|
|
|
|
|
Choices = ["sigmoid", "tanh", "relu", "identity"],
|
|
|
|
|
default "tanh".
|
|
|
|
|
dtype(str): Data type. Choices = ["float32", "float64"], default "float32".
|
|
|
|
|
name(str|None): A name for this layer(optional). If set None, the layer
|
|
|
|
|
will be named automatically.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
tuple: The projection of hidden state, and cell state of LSTMP. The \
|
|
|
|
|
shape of projection is (T x P), for the cell state which is \
|
|
|
|
|
(T x D), and both LoD is the same with the `input`.
|
|
|
|
|
tuple: A tuple of two output variable: the projection of hidden state, \
|
|
|
|
|
and cell state of LSTMP. The shape of projection is (T x P), \
|
|
|
|
|
for the cell state which is (T x D), and both LoD is the same \
|
|
|
|
|
with the `input`.
|
|
|
|
|
|
|
|
|
|
Examples:
|
|
|
|
|
|
|
|
|
|
.. code-block:: python
|
|
|
|
|
|
|
|
|
|
dict_dim, emb_dim = 128, 64
|
|
|
|
|
data = fluid.layers.data(name='sequence', shape=[1],
|
|
|
|
|
dtype='int32', lod_level=1)
|
|
|
|
|
emb = fluid.layers.embedding(input=data, size=[dict_dim, emb_dim])
|
|
|
|
|
hidden_dim, proj_dim = 512, 256
|
|
|
|
|
fc_out = fluid.layers.fc(input=input_seq, size=hidden_dim * 4,
|
|
|
|
|
fc_out = fluid.layers.fc(input=emb, size=hidden_dim * 4,
|
|
|
|
|
act=None, bias_attr=None)
|
|
|
|
|
proj_out, _ = fluid.layers.dynamic_lstmp(input=fc_out,
|
|
|
|
|
size=hidden_dim * 4,
|
|
|
|
|
@ -626,10 +629,10 @@ def dynamic_gru(input,
|
|
|
|
|
candidate_activation='tanh',
|
|
|
|
|
h_0=None):
|
|
|
|
|
"""
|
|
|
|
|
**Dynamic GRU Layer**
|
|
|
|
|
**Gated Recurrent Unit (GRU) Layer**
|
|
|
|
|
|
|
|
|
|
Refer to `Empirical Evaluation of Gated Recurrent Neural Networks on
|
|
|
|
|
Sequence Modeling <https://arxiv.org/abs/1412.3555>`_
|
|
|
|
|
Sequence Modeling <https://arxiv.org/abs/1412.3555>`_ .
|
|
|
|
|
|
|
|
|
|
The formula is as follows:
|
|
|
|
|
|
|
|
|
|
@ -676,17 +679,25 @@ def dynamic_gru(input,
|
|
|
|
|
Choices = ["sigmoid", "tanh", "relu", "identity"], default "sigmoid".
|
|
|
|
|
candidate_activation(str): The activation for candidate hidden state.
|
|
|
|
|
Choices = ["sigmoid", "tanh", "relu", "identity"], default "tanh".
|
|
|
|
|
h_0 (Variable): The hidden output of the first time step.
|
|
|
|
|
h_0 (Variable): This is initial hidden state. If not set, default is
|
|
|
|
|
zero. This is a tensor with shape (N x D), where N is the number of
|
|
|
|
|
total time steps of input mini-batch feature and D is the hidden
|
|
|
|
|
size.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Variable: The hidden state of GRU. The shape is :math:`(T \\times D)`, \
|
|
|
|
|
and lod is the same with the input.
|
|
|
|
|
and sequence length is the same with the input.
|
|
|
|
|
|
|
|
|
|
Examples:
|
|
|
|
|
|
|
|
|
|
.. code-block:: python
|
|
|
|
|
|
|
|
|
|
dict_dim, emb_dim = 128, 64
|
|
|
|
|
data = fluid.layers.data(name='sequence', shape=[1],
|
|
|
|
|
dtype='int32', lod_level=1)
|
|
|
|
|
emb = fluid.layers.embedding(input=data, size=[dict_dim, emb_dim])
|
|
|
|
|
hidden_dim = 512
|
|
|
|
|
x = fluid.layers.fc(input=data, size=hidden_dim * 3)
|
|
|
|
|
x = fluid.layers.fc(input=emb, size=hidden_dim * 3)
|
|
|
|
|
hidden = fluid.layers.dynamic_gru(input=x, dim=hidden_dim)
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
@ -924,13 +935,13 @@ def dropout(x, dropout_prob, is_test=False, seed=None, name=None):
|
|
|
|
|
|
|
|
|
|
Drop or keep each element of `x` independently. Dropout is a regularization
|
|
|
|
|
technique for reducing overfitting by preventing neuron co-adaption during
|
|
|
|
|
training. The dropout operator randomly set (according to the given dropout
|
|
|
|
|
training. The dropout operator randomly sets (according to the given dropout
|
|
|
|
|
probability) the outputs of some units to zero, while others are remain
|
|
|
|
|
unchanged.
|
|
|
|
|
|
|
|
|
|
Args:
|
|
|
|
|
x (Variable): The input tensor.
|
|
|
|
|
dropout_prob (float): Probability of setting units to zero.
|
|
|
|
|
x (Variable): The input tensor variable.
|
|
|
|
|
dropout_prob (float): Probability of setting units to zero.
|
|
|
|
|
is_test (bool): A flag indicating whether it is in test phrase or not.
|
|
|
|
|
seed (int): A Python integer used to create random seeds. If this
|
|
|
|
|
parameter is set to None, a random seed is used.
|
|
|
|
|
@ -940,13 +951,14 @@ def dropout(x, dropout_prob, is_test=False, seed=None, name=None):
|
|
|
|
|
will be named automatically.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Variable: A tensor variable.
|
|
|
|
|
Variable: A tensor variable is the shape with `x`.
|
|
|
|
|
|
|
|
|
|
Examples:
|
|
|
|
|
|
|
|
|
|
.. code-block:: python
|
|
|
|
|
|
|
|
|
|
x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
|
|
|
|
|
droped = fluid.layers.dropout(input=x, dropout_rate=0.5)
|
|
|
|
|
x = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
|
|
|
|
|
droped = fluid.layers.dropout(x, dropout_prob=0.5)
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
helper = LayerHelper('dropout', **locals())
|
|
|
|
|
@ -1235,14 +1247,17 @@ def conv2d(input,
|
|
|
|
|
act=None,
|
|
|
|
|
name=None):
|
|
|
|
|
"""
|
|
|
|
|
**Convlution2D Layer**
|
|
|
|
|
|
|
|
|
|
The convolution2D layer calculates the output based on the input, filter
|
|
|
|
|
and strides, paddings, dilations, groups parameters. Input(Input) and
|
|
|
|
|
Output(Output) are in NCHW format. Where N is batch size, C is the number of
|
|
|
|
|
and strides, paddings, dilations, groups parameters. Input and
|
|
|
|
|
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 details of convolution layer, please refer UFLDL's `convolution,
|
|
|
|
|
<http://ufldl.stanford.edu/tutorial/supervised/FeatureExtractionUsingConvolution/>`_ .
|
|
|
|
|
Filter is in MCHW format, where M is the number of output image channels,
|
|
|
|
|
C is the number of input image channels, H is the height of the filter,
|
|
|
|
|
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.
|
|
|
|
|
Please refer to UFLDL's `convolution
|
|
|
|
|
<http://ufldl.stanford.edu/tutorial/supervised/FeatureExtractionUsingConvolution/>`_
|
|
|
|
|
for more detials.
|
|
|
|
|
If bias attribution and activation type are provided, bias is added to the
|
|
|
|
|
output of the convolution, and the corresponding activation function is
|
|
|
|
|
applied to the final result.
|
|
|
|
|
@ -1253,15 +1268,14 @@ def conv2d(input,
|
|
|
|
|
|
|
|
|
|
Out = \sigma (W \\ast X + b)
|
|
|
|
|
|
|
|
|
|
In the above equation:
|
|
|
|
|
Where:
|
|
|
|
|
|
|
|
|
|
* :math:`X`: Input value, a tensor with NCHW format.
|
|
|
|
|
* :math:`W`: Filter value, a tensor with MCHW format.
|
|
|
|
|
* :math:`\\ast`: Convolution operation.
|
|
|
|
|
* :math:`b`: Bias value, a 2-D tensor with shape [M, 1].
|
|
|
|
|
* :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.
|
|
|
|
|
|
|
|
|
|
Example:
|
|
|
|
|
|
|
|
|
|
@ -1272,6 +1286,7 @@ def conv2d(input,
|
|
|
|
|
Filter shape: :math:`(C_{out}, C_{in}, H_f, W_f)`
|
|
|
|
|
|
|
|
|
|
- Output:
|
|
|
|
|
|
|
|
|
|
Output shape: :math:`(N, C_{out}, H_{out}, W_{out})`
|
|
|
|
|
|
|
|
|
|
Where
|
|
|
|
|
@ -1283,7 +1298,7 @@ def conv2d(input,
|
|
|
|
|
|
|
|
|
|
Args:
|
|
|
|
|
input (Variable): The input image with [N, C, H, W] format.
|
|
|
|
|
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.
|
|
|
|
|
filter_size (int|tuple|None): The filter size. If filter_size is a tuple,
|
|
|
|
|
it must contain two integers, (filter_size_H, filter_size_W).
|
|
|
|
|
@ -1306,7 +1321,8 @@ def conv2d(input,
|
|
|
|
|
bias_attr (ParamAttr): Bias parameter for the Conv2d layer. Default: None
|
|
|
|
|
use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn
|
|
|
|
|
library is installed. Default: True
|
|
|
|
|
use_mkldnn (bool): Use mkldnn kernels or not.
|
|
|
|
|
use_mkldnn (bool): Use mkldnn kernels or not, it is valid only when compiled
|
|
|
|
|
with mkldnn library. Default: False
|
|
|
|
|
act (str): Activation type. Default: None
|
|
|
|
|
name (str|None): A name for this layer(optional). If set None, the layer
|
|
|
|
|
will be named automatically.
|
|
|
|
|
@ -2987,32 +3003,33 @@ def l2_normalize(x, axis, epsilon=1e-12, name=None):
|
|
|
|
|
norm. For a 1-D tensor (`dim` is fixed to 0), this layer computes
|
|
|
|
|
|
|
|
|
|
.. math::
|
|
|
|
|
y = \frac{x}{ \sqrt{\sum {x^2} + epsion }}
|
|
|
|
|
|
|
|
|
|
y = \\frac{x}{ \sqrt{\sum {x^2} + epsion }}
|
|
|
|
|
|
|
|
|
|
For `x` with more dimensions, this layer independently normalizes each 1-D
|
|
|
|
|
slice along dimension `axis`.
|
|
|
|
|
|
|
|
|
|
Args:
|
|
|
|
|
x(Variable|list): The input tensor to l2_normalize layer.
|
|
|
|
|
axis(int): The axis on which to apply normalization. If `axis < 0`,
|
|
|
|
|
axis(int): The axis on which to apply normalization. If `axis < 0`, \
|
|
|
|
|
the dimension to normalization is rank(X) + axis. -1 is the
|
|
|
|
|
last dimension.
|
|
|
|
|
epsilon(float): The epsilon value is used to avoid division by zero,
|
|
|
|
|
epsilon(float): The epsilon value is used to avoid division by zero, \
|
|
|
|
|
the defalut value is 1e-10.
|
|
|
|
|
name(str|None): A name for this layer(optional). If set None, the layer
|
|
|
|
|
name(str|None): A name for this layer(optional). If set None, the layer \
|
|
|
|
|
will be named automatically.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Variable: The output tensor variable.
|
|
|
|
|
Variable: The output tensor variable is the same shape with `x`.
|
|
|
|
|
|
|
|
|
|
Examples:
|
|
|
|
|
|
|
|
|
|
.. code-block:: python
|
|
|
|
|
|
|
|
|
|
data = fluid.layers.data(name="data",
|
|
|
|
|
shape=(3, 17, 13),
|
|
|
|
|
dtype="float32")
|
|
|
|
|
normed = fluid.layers.l2_normalize(x=data, axis=1)
|
|
|
|
|
data = fluid.layers.data(name="data",
|
|
|
|
|
shape=(3, 17, 13),
|
|
|
|
|
dtype="float32")
|
|
|
|
|
normed = fluid.layers.l2_normalize(x=data, axis=1)
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
if len(x.shape) == 1:
|
|
|
|
|
|
Yibing Liu
7 years ago