Skip to content

P
pytensor
提交 62966940 authored 作者: Arnaud Bergeron's avatar Arnaud Bergeron
浏览文件
操作

Fix the docstrings in abstract_conv.py

上级 abe2d24c
显示空白字符变更
内嵌 并排
正在显示 包含 133 行增加 和 111 行删除
theano/tensor/nnet/abstract_conv.py
浏览文件 @ 62966940
...@@ -132,68 +132,80 @@ def conv2d_grad_wrt_inputs(output_grad, ...@@ -132,68 +132,80 @@ def conv2d_grad_wrt_inputs(output_grad,
used by the convolution, such that the output_grad is upsampled used by the convolution, such that the output_grad is upsampled
to the input shape. to the input shape.
:type output_grad: symbolic 4D tensor. Parameters
:param output_grad: mini-batch of feature map stacks, of shape ----------
(batch size, input channels, input rows, input columns). output_grad : symbolic 4D tensor
This is the tensor that will be upsampled or the output mini-batch of feature map stacks, of shape (batch size, input
gradient of the convolution whose gradient will be taken channels, input rows, input columns). This is the tensor that
with respect to the input of the convolution. will be upsampled or the output gradient of the convolution
See the optional parameter ``output_grad_shape``. whose gradient will be taken with respect to the input of the
convolution. See the optional parameter
:type filters: symbolic 4D tensor. ``output_grad_shape``.
:param filters: set of filters used in CNN layer of shape filters : symbolic 4D tensor
(output channels, input channels, filter rows, filter columns). set of filters used in CNN layer of shape (output channels,
See the optional parameter ``filter_shape``. input channels, filter rows, filter columns). See the
optional parameter ``filter_shape``.
:type output_grad_shape: None, tuple/list of len 4 of int or output_grad_shape : list of 4 symbolic or real ints
Constant variable. The shape of the output_grad parameter. Optional, possibly
:param output_grad_shape: The shape of the output_grad parameter. used to choose an optimal implementation. You can give
Optional, possibly used to choose an optimal implementation. ``None`` for any element of the list to specify that this
You can give ``None`` for any element of the list to specify that this
element is not known at compile time. element is not known at compile time.
input_shape : list of 2 symbolic or real ints
The shape (row and column size) of the input (upsampled)
parameter. Not Optional, since given the output_grad_shape
and the subsample values, multiple input_shape may be
plausible.
filter_shape : list of 4 symbolic or real ints
The shape of the filters parameter. Optional, possibly used
to choose an optimal implementation. You can give ``None``
for any element of the list to specify that this element is
not known at compile time.
border_mode : str, int or tuple of two int
Either of the following:
:type input_shape: tuple/list of len 2 of int or Constant variable. ``'valid'``
:param input_shape: The shape (row and column size) of the apply filter wherever it completely overlaps with the
input (upsampled) parameter. input. Generates output of shape: input shape - filter
Not Optional, since given the output_grad_shape and the subsample values, shape + 1
multiple input_shape may be plausible.
:type filter_shape: None, tuple/list of len 4 of int or Constant variable ``'full'``
:param filter_shape: The shape of the filters parameter. apply filter wherever it partly overlaps with the input.
Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this
element is not known at compile time.
:type border_mode: str, int or tuple of two int
:param border_mode: Either of the following:
* ``'valid'``: apply filter wherever it completely overlaps with the
input. Generates output of shape: input shape - filter shape + 1
* ``'full'``: apply filter wherever it partly overlaps with the input.
Generates output of shape: input shape + filter shape - 1 Generates output of shape: input shape + filter shape - 1
* ``'half'``: pad input with a symmetric border of ``filter rows // 2``
rows and ``filter columns // 2`` columns, then perform a valid ``'half'``
convolution. For filters with an odd number of rows and columns, this pad input with a symmetric border of ``filter rows // 2``
leads to the output shape being equal to the input shape. rows and ``filter columns // 2`` columns, then perform a
* ``int``: pad input with a symmetric border of zeros of the given valid convolution. For filters with an odd number of rows
and columns, this leads to the output shape being equal to
the input shape.
``int``
pad input with a symmetric border of zeros of the given
width, then perform a valid convolution. width, then perform a valid convolution.
* ``(int1, int2)``: pad input with a symmetric border of ``int1`` rows
and ``int2`` columns, then perform a valid convolution.
:type subsample: tuple of len 2, the subsampling used in the forward pass ``(int1, int2)``
of the convolutional operation. pad input with a symmetric border of ``int1`` rows and
:param subsample: factor by which to subsample the output. ``int2`` columns, then perform a valid convolution.
Also called strides elsewhere.
:type filter_flip: bool subsample : tuple of len 2
:param filter_flip: If ``True``, will flip the filter rows and columns The subsampling used in the forward pass. Also called strides
before sliding them over the input. This operation is normally referred elsewhere.
to as a convolution, and this is the default. If ``False``, the filters filter_flip : bool
are not flipped and the operation is referred to as a If ``True``, will flip the filter rows and columns before
cross-correlation. sliding them over the input. This operation is normally
referred to as a convolution, and this is the default. If
``False``, the filters are not flipped and the operation is
referred to as a cross-correlation.
Returns
-------
symbolic 4D tensor
set of feature maps generated by convolutional layer. Tensor
is of shape (batch size, output channels, output rows, output
columns)
:rtype: symbolic 4D tensor. Notes
:return: set of feature maps generated by convolutional layer. Tensor is -----
of shape (batch size, output channels, output rows, output columns)
:note: If CuDNN is available, it will be used on the :note: If CuDNN is available, it will be used on the
GPU. Otherwise, it is the *CorrMM* convolution that will be used GPU. Otherwise, it is the *CorrMM* convolution that will be used
...@@ -224,71 +236,81 @@ def conv2d_grad_wrt_weights(input, ...@@ -224,71 +236,81 @@ def conv2d_grad_wrt_weights(input,
"""This function will build the symbolic graph for getting the """This function will build the symbolic graph for getting the
gradient of the output of a convolution (output_grad) w.r.t its wights. gradient of the output of a convolution (output_grad) w.r.t its wights.
:type input: symbolic 4D tensor. Parameters
:param input: mini-batch of feature map stacks, of shape ----------
(batch size, input channels, input rows, input columns). input : symbolic 4D tensor
This is the input of the convolution in the forward pass. mini-batch of feature map stacks, of shape (batch size, input
channels, input rows, input columns). This is the input of
:type output_grad: symbolic 4D tensor. the convolution in the forward pass.
:param output_grad: mini-batch of feature map stacks, of shape output_grad : symbolic 4D tensor
(batch size, input channels, input rows, input columns). mini-batch of feature map stacks, of shape (batch size, input
This is the gradient of the output of convolution. channels, input rows, input columns). This is the gradient of
the output of convolution.
:type filters: symbolic 4D tensor. filters : symbolic 4D tensor.
:param filters: set of filters used in CNN layer of shape set of filters used in CNN layer of shape (output channels,
(output channels, input channels, filter rows, filter columns). input channels, filter rows, filter columns). See the
See the optional parameter ``filter_shape``. optional parameter ``filter_shape``.
output_grad_shape : list of 4 ints or Constant variables
:type output_grad_shape: None, tuple/list of len 4 of int The shape of the input parameter. Optional, possibly used to
or Constant variable. choose an optimal implementation. You can give ``None`` for
:param output_grad_shape: The shape of the input parameter. any element of the list to specify that this element is not
Optional, possibly used to choose an optimal implementation. known at compile time.
You can give ``None`` for any element of the list to specify that this input_shape : list of 2 ints or Constant variables
element is not known at compile time. The shape of the input parameter. This parameter indicates
the row and column size of the input in the forward pass.
:type input_shape: tuple/list of len 2 of int or Constant variable.
:param input_shape: The shape of the input parameter.
This parameter indicates the row and column size of the input
in the forward pass.
Optional, possibly used to choose an optimal implementation. Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this You can give ``None`` for any element of the list to specify
element is not known at compile time. that this element is not known at compile time.
filter_shape : list of 4 ints or Constant variables
The shape of the filters parameter. Not Optional, since given
the output_grad_shape and the input_shape, multiple
filter_shape may be plausible.
border_mode : str, int or tuple of two ints
Either of the following:
:type filter_shape: None, tuple/list of len 4 of int or Constant variable. ``'valid'``
:param filter_shape: The shape of the filters parameter. apply filter wherever it completely overlaps with the
Not Optional, since given the output_grad_shape and the input_shape, input. Generates output of shape: input shape - filter
multiple filter_shape may be plausible. shape + 1
:type border_mode: str, int or tuple of two int ``'full'``
:param border_mode: Either of the following: apply filter wherever it partly overlaps with the input.
* ``'valid'``: apply filter wherever it completely overlaps with the
input. Generates output of shape: input shape - filter shape + 1
* ``'full'``: apply filter wherever it partly overlaps with the input.
Generates output of shape: input shape + filter shape - 1 Generates output of shape: input shape + filter shape - 1
* ``'half'``: pad input with a symmetric border of ``filter rows // 2``
rows and ``filter columns // 2`` columns, then perform a valid ``'half'``
convolution. For filters with an odd number of rows and columns, this pad input with a symmetric border of ``filter rows // 2``
leads to the output shape being equal to the input shape. rows and ``filter columns // 2`` columns, then perform a
* ``int``: pad input with a symmetric border of zeros of the given valid convolution. For filters with an odd number of rows
and columns, this leads to the output shape being equal to
the input shape.
``int``
pad input with a symmetric border of zeros of the given
width, then perform a valid convolution. width, then perform a valid convolution.
* ``(int1, int2)``: pad input with a symmetric border of ``int1`` rows
and ``int2`` columns, then perform a valid convolution.
:type subsample: tuple of len 2, the subsampling used in the forward pass ``(int1, int2)``
of the convolutional operation. pad input with a symmetric border of ``int1`` rows and
:param subsample: factor by which to subsample the output. ``int2`` columns, then perform a valid convolution.
Also called strides elsewhere.
:type filter_flip: bool subsample : tuple of len 2
:param filter_flip: If ``True``, will flip the filter rows and columns The subsampling used in the forward pass of the convolutional
before sliding them over the input. This operation is normally referred operation. Also called strides elsewhere.
to as a convolution, and this is the default. If ``False``, the filters filter_flip : bool
are not flipped and the operation is referred to as a If ``True``, will flip the filter rows and columns before
cross-correlation. sliding them over the input. This operation is normally
referred to as a convolution, and this is the default. If
``False``, the filters are not flipped and the operation is
referred to as a cross-correlation.
Returns
-------
symbolic 4D tensor
set of feature maps generated by convolutional layer. Tensor
is of shape (batch size, output channels, output rows, output
columns)
:rtype: symbolic 4D tensor. Notes
:return: set of feature maps generated by convolutional layer. Tensor is -----
of shape (batch size, output channels, output rows, output columns)
:note: If CuDNN is available, it will be used on the :note: If CuDNN is available, it will be used on the
GPU. Otherwise, it is the *CorrMM* convolution that will be used GPU. Otherwise, it is the *CorrMM* convolution that will be used
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论