tensorflow::ops::Conv2D

#include <nn_ops.h>

Computes a 2-D convolution given 4-D input and filter tensors.

Summary

Given an input tensor of shape [batch, in_height, in_width, in_channels] and a filter / kernel tensor of shape [filter_height, filter_width, in_channels, out_channels], this op performs the following:

  1. Flattens the filter to a 2-D matrix with shape [filter_height * filter_width * in_channels, output_channels].
  2. Extracts image patches from the input tensor to form a virtual tensor of shape [batch, out_height, out_width, filter_height * filter_width * in_channels].
  3. For each patch, right-multiplies the filter matrix and the image patch vector.

In detail, with the default NHWC format,

output[b, i, j, k] =
    sum_{di, dj, q} input[b, strides[1] * i + di, strides[2] * j + dj, q] *
                    filter[di, dj, q, k]

Must have strides[0] = strides[3] = 1. For the most common case of the same horizontal and vertices strides, strides = [1, stride, stride, 1].

Args:

  • scope: A Scope object
  • input: A 4-D tensor. The dimension order is interpreted according to the value of data_format, see below for details.
  • filter: A 4-D tensor of shape [filter_height, filter_width, in_channels, out_channels]
  • strides: 1-D tensor of length 4. The stride of the sliding window for each dimension of input. The dimension order is determined by the value of data_format, see below for details.
  • padding: The type of padding algorithm to use.

Optional attributes (see Attrs):

  • explicit_paddings: If padding is "EXPLICIT", the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is explicit_paddings[2 * i] and explicit_paddings[2 * i + 1], respectively. If padding is not "EXPLICIT", explicit_paddings must be empty.
  • data_format: Specify the data format of the input and output data. With the default format "NHWC", the data is stored in the order of: [batch, height, width, channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, channels, height, width].
  • dilations: 1-D tensor of length 4. The dilation factor for each dimension of input. If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of data_format, see above for details. Dilations in the batch and depth dimensions must be 1.

Returns:

  • Output: A 4-D tensor. The dimension order is determined by the value of data_format, see below for details.

Constructors and Destructors

Conv2D(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input filter, const gtl::ArraySlice< int > & strides, StringPiece padding)
Conv2D(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input filter, const gtl::ArraySlice< int > & strides, StringPiece padding, const Conv2D::Attrs & attrs)

Public attributes

operation
output

Public functions

node() const
::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public static functions

DataFormat(StringPiece x)
Dilations(const gtl::ArraySlice< int > & x)
ExplicitPaddings(const gtl::ArraySlice< int > & x)
UseCudnnOnGpu(bool x)

Structs

tensorflow::ops::Conv2D::Attrs

Optional attribute setters for Conv2D.

Public attributes

operation

Operation operation

output

::tensorflow::Output output

Public functions

Conv2D

 Conv2D(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input filter,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding
)

Conv2D

 Conv2D(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input filter,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding,
  const Conv2D::Attrs & attrs
)

node

::tensorflow::Node * node() const 

operator::tensorflow::Input

 operator::tensorflow::Input() const 

operator::tensorflow::Output

 operator::tensorflow::Output() const 

Public static functions

DataFormat

Attrs DataFormat(
  StringPiece x
)

Dilations

Attrs Dilations(
  const gtl::ArraySlice< int > & x
)

ExplicitPaddings

Attrs ExplicitPaddings(
  const gtl::ArraySlice< int > & x
)

UseCudnnOnGpu

Attrs UseCudnnOnGpu(
  bool x
)