m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Polish the english documentation and example of paddle.nn.Linear and paddle.nn.functional.linear (#27759)

Browse Source
my_2.0rc
Yiqun Liu 4 years ago committed by GitHub
parent 631c1f3018
commit 836ee3b0c8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 87 additions and 66 deletions
Show Stats Download Patch File Download Diff File

3
python/paddle/fluid/dygraph/nn.py
Unescape View File

@ -895,9 +895,6 @@ class Pool2D(layers.Layer):
class Linear(layers.Layer):
"""
:alias_main: paddle.nn.Linear
:alias: paddle.nn.Linear,paddle.nn.layer.Linear,paddle.nn.layer.common.Linear
:old_api: paddle.fluid.dygraph.Linear
Fully-connected linear transformation layer:

59
python/paddle/nn/functional/common.py
Unescape View File

@ -1406,46 +1406,53 @@ def cosine_similarity(x1, x2, axis=1, eps=1e-8):
def linear(x, weight, bias=None, name=None):
"""
Fully-connected linear transformation op
Fully-connected linear transformation operator. For each input :math:`X` ,
the equation is:
.. math::
Out = {XW + b}
Out = XW + b
where :math:`X` is the input Tensor, :math:`W` and :math:`b` are weight and bias respectively.
where :math:`W` is the weight and :math:`b` is the bias.
The linear op multiplies input tensor with weight matrix and
produces an output Tensor of shape [N, *, output_dim],
where N is batch size and `*` means any number of additional dimensions and output_dim is the last dim of ``weight``.
If ``bias`` is not None, a bias will be added to the output.
If the weight is a 2-D tensor of shape :math:`[in\_features, out\_features]` ,
input should be a multi-dimensional tensor of shape
:math:`[batch\_size, *, in\_features]` , where :math:`*` means any number of
additional dimensions. The linear operator multiplies input tensor with
weight and produces an output tensor of shape :math:`[batch\_size, *, out\_features]` ,
If :math:`bias` is not None, the bias should be a 1-D tensor of shape
:math:`[out\_features]` and will be added to the output.
Args:
x(Tensor): Input tensor, its data type is float16, float32 or float64
weight(Tensor): Weight tensor, its data type is float16, float32 or float64
bias(Tensor|None, optional): Bias tensor, its data type is float16, float32 or float64. If it is set to None, no bias will be added to the output units.
name(str|None, optional): For detailed information, please refer to :ref:`api_guide_Name`. Default: None.
Parameters:
x (Tensor): Input tensor. The data type should be float16, float32 or float64.
weight (Tensor): Weight tensor. The data type should be float16, float32 or float64.
bias (Tensor, optional): Bias tensor. The data type should be float16, float32 or float64.
If it is set to None, no bias will be added to the output units.
name (str, optional): Normally there is no need for user to set this parameter.
For detailed information, please refer to :ref:`api_guide_Name` .
Returns:
Output tensor
Tensor, the shape is :math:`[batch\_size, *, out\_features]` and the
data type is the same with input :math:`x` .
Examples:
.. code-block:: python
import numpy as np
import paddle
import paddle.nn.functional as F
input = np.ones((3,1,2), dtype=np.float32)
weight = np.ones((2,2), dtype=np.float32)
bias = np.ones((2), dtype=np.float32)
place = paddle.CPUPlace()
paddle.disable_static(place)
input = paddle.to_tensor(input)
weight = paddle.to_tensor(weight)
bias = paddle.to_tensor(bias)
out = F.linear(input, weight, bias)
print(out) #[3 3 3 3 3 3]
x = paddle.randn((3, 2), dtype="float32")
# x: [[-0.32342386 -1.200079 ]
# [ 0.7979031 -0.90978354]
# [ 0.40597573 1.8095392 ]]
weight = paddle.full(shape=[2, 4], fill_value="0.5", dtype="float32", name="weight")
# weight: [[0.5 0.5 0.5 0.5]
# [0.5 0.5 0.5 0.5]]
bias = paddle.ones(shape=[4], dtype="float32", name="bias")
# bias: [1. 1. 1. 1.]
y = paddle.nn.functional.linear(x, weight, bias)
# y: [[0.23824859 0.23824859 0.23824859 0.23824859]
# [0.9440598 0.9440598 0.9440598 0.9440598 ]
# [2.1077576 2.1077576 2.1077576 2.1077576 ]]
"""
if in_dygraph_mode():
pre_bias = _varbase_creator(dtype=x.dtype)

91
python/paddle/nn/layer/common.py
Unescape View File

@ -15,7 +15,6 @@
# TODO: define the common classes to build a neural network
from ...fluid.dygraph import BilinearTensorProduct #DEFINE_ALIAS
from ...fluid.dygraph import Pool2D #DEFINE_ALIAS
from ...fluid.dygraph import Linear #DEFINE_ALIAS
from ...fluid.dygraph import Flatten #DEFINE_ALIAS
from ...fluid.dygraph import layers
from .. import functional as F
@ -50,56 +49,74 @@ __all__ = [
class Linear(layers.Layer):
"""
Fully-connected linear transformation layer:
Fully-connected linear transformation layer. For each input :math:`X` ,
the equation is:
.. math::
Out = {XW + b}
Out = XW + b
where :math:`X` is the input Tensor, :math:`W` and :math:`b` are weight and bias respectively.
where :math:`W` is the weight and :math:`b` is the bias.
Linear layer takes only one ``Tensor`` input.
The Linear layer multiplies input tensor with weight matrix and
produces an output Tensor of shape [N, *, `output_dim`],
where N is batch size and `*` means any number of additional dimensions.
If ``bias_attr`` is not None, a bias variable will be created and added to the output.
Linear layer takes only one multi-dimensional tensor as input with the
shape :math:`[batch\_size, *, in\_features]` , where :math:`*` means any
number of additional dimensions. It multiplies input tensor with the weight
(a 2-D tensor of shape :math:`[in\_features, out\_features]` ) and produces
an output tensor of shape :math:`[batch\_size, *, out\_features]` .
If :math:`bias\_attr` is not False, the bias (a 1-D tensor of
shape :math:`[out\_features]` ) will be created and added to the output.
Parameters:
in_features(int): The number of input units in this layer.
out_features(int): The number of output units in this layer.
weight_attr(ParamAttr or list of ParamAttr, optional): The parameter attribute for learnable
weights(Parameter) of this layer. Default: None.
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.
If it is set to None, the bias is initialized zero. Default: None.
name(str|None): For detailed information, please refer to :ref:`api_guide_Name`. Default: None.
Attributes:
**weight** (Parameter): the learnable weights of this layer.
in_features (int): The number of input units.
out_features (int): The number of output units.
weight_attr (ParamAttr, optional): The attribute for the learnable
weight of this layer. The default value is None and the weight will be
initialized to zero. For detailed information, please refer to
paddle.ParamAttr.
bias_attr (ParamAttr|bool, optional): The attribute for the learnable bias
of this layer. If it is set to False, no bias will be added to the output.
If it is set to None or one kind of ParamAttr, a bias parameter will
be created according to ParamAttr. For detailed information, please refer
to paddle.ParamAttr. The default value is None and the bias will be
initialized to zero.
name (str, optional): Normally there is no need for user to set this parameter.
For detailed information, please refer to :ref:`api_guide_Name` .
**bias** (Parameter or None): the learnable bias of this layer.
Attribute:
**weight** (Parameter): the learnable weight of this layer.
Returns:
None
**bias** (Parameter): the learnable bias of this layer.
Shape:
- input: Multi-dimentional tensor with shape :math:`[batch\_size, *, in\_features]` .
- output: Multi-dimentional tensor with shape :math:`[batch\_size, *, out\_features]` .
Examples:
.. code-block:: python
import paddle
from paddle import nn
import numpy as np
data = np.ones((3,1,2), np.float32)
place = paddle.CPUPlace()
paddle.disable_static(place)
data = paddle.to_tensor(data)
weight_attr=paddle.framework.ParamAttr(name="linear_weight", learning_rate=1.0,
trainable=False, regularizer=None, initializer=paddle.fluid.initializer.ConstantInitializer(value=1.0))
bias_attr=paddle.framework.ParamAttr(name="linear_bias", learning_rate=1.0,
trainable=False, regularizer=None, initializer=paddle.fluid.initializer.ConstantInitializer(value=1.0))
linear = nn.Linear(2,2,weight_attr=weight_attr, bias_attr=bias_attr)
res = linear(data) # [3 3 3 3 3 3]
# Define the linear layer.
weight_attr = paddle.ParamAttr(
name="weight",
initializer=paddle.nn.initializer.Constant(value=0.5))
bias_attr = paddle.ParamAttr(
name="bias",
initializer=paddle.nn.initializer.Constant(value=1.0))
linear = paddle.nn.Linear(2, 4, weight_attr=weight_attr, bias_attr=bias_attr)
# linear.weight: [[0.5 0.5 0.5 0.5]
# [0.5 0.5 0.5 0.5]]
# linear.bias: [1. 1. 1. 1.]
x = paddle.randn((3, 2), dtype="float32")
# x: [[-0.32342386 -1.200079 ]
# [ 0.7979031 -0.90978354]
# [ 0.40597573 1.8095392 ]]
y = linear(x)
# y: [[0.23824859 0.23824859 0.23824859 0.23824859]
# [0.9440598 0.9440598 0.9440598 0.9440598 ]
# [2.1077576 2.1077576 2.1077576 2.1077576 ]]
"""
def __init__(self,

Write Preview
Loading…
Cancel
Save