Link Search Menu Expand Document

DepthwiseConv2dNativeBackpropInput


tensorflow C++ API

tensorflow::ops::DepthwiseConv2dNativeBackpropInput

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


Summary

Arguments:

  • scope: A Scope object
  • input_sizes: An integer vector representing the shape ofinput, based ondata_format. For example, ifdata_formatis ‘NHWC’ theninputis a 4-D[batch, height, width, channels]tensor.
  • filter: 4-D with shape[filter_height, filter_width, in_channels, depthwise_multiplier].
  • out_backprop: 4-D with shape based ondata_format. For example, ifdata_formatis ‘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 (seeAttrs):

  • 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].

Returns:

  • Output: 4-D with shape according todata_format. For example, ifdata_formatis ‘NHWC’, output shape is [batch, in_height, in_width, in_channels]. Gradient w.r.t. the input of the convolution.

DepthwiseConv2dNativeBackpropInput block

Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_nn.cpp

Argument:

  • Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
  • Input input_sizes: connect Input node.
  • Input filter: connect Input node.
  • Input out_backprop: connect Input node.
  • gtl::ArraySlice< int > strides: Input strides in value ex)1,2,2,1
  • StringPiece padding: Input padding in value ex)SAME
  • DepthwiseConv2dNativeBackpropInput::Attrs attrs : Input attrs in value. ex) data_format_ = NHWC;

Return:

  • Output output : Output object of DepthwiseConv2dNativeBackpropInput class object.

Result:

  • std::vector(Tensor) result_output : Returned object of executed result by calling session.

Using Method