W3cubDocs

/TensorFlow C++

tensorflow::ops::DepthwiseConv2dNativeBackpropFilter

#include <nn_ops.h>

Computes the gradients of depthwise convolution with respect to the filter.

Summary

Arguments:

  • scope: A Scope object
  • input: 4-D with shape based on data_format. For example, if data_format is 'NHWC' then input is a 4-D [batch, in_height, in_width, in_channels] tensor.
  • filter_sizes: An integer vector representing the tensor shape of filter, where filter is a 4-D [filter_height, filter_width, in_channels, depthwise_multiplier] tensor.
  • out_backprop: 4-D with shape based on data_format. For example, if data_format is 'NHWC' then out_backprop shape is [batch, out_height, out_width, out_channels]. Gradients w.r.t. the output of the convolution.
  • strides: The stride of the sliding window for each dimension of the input of the convolution.
  • padding: The type of padding algorithm to use.

Optional attributes (see Attrs):

  • 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: 4-D with shape [filter_height, filter_width, in_channels, out_channels]. Gradient w.r.t. the filter input of the convolution.
Constructors and Destructors
DepthwiseConv2dNativeBackpropFilter(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input filter_sizes, ::tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding)
DepthwiseConv2dNativeBackpropFilter(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input filter_sizes, ::tensorflow::Input out_backprop, const gtl::ArraySlice< int > & strides, StringPiece padding, const DepthwiseConv2dNativeBackpropFilter::Attrs & attrs)
Public attributes
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)
Structs
tensorflow::ops::DepthwiseConv2dNativeBackpropFilter::Attrs

Optional attribute setters for DepthwiseConv2dNativeBackpropFilter.

Public attributes

output

::tensorflow::Output output

Public functions

DepthwiseConv2dNativeBackpropFilter

 DepthwiseConv2dNativeBackpropFilter(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input filter_sizes,
  ::tensorflow::Input out_backprop,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding
)

DepthwiseConv2dNativeBackpropFilter

 DepthwiseConv2dNativeBackpropFilter(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input filter_sizes,
  ::tensorflow::Input out_backprop,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding,
  const DepthwiseConv2dNativeBackpropFilter::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
)

© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/depthwise-conv2d-native-backprop-filter.html