Watch keynotes, product sessions, workshops, and more from Google I/O See playlist

DepthwiseConv2dNativeBackpropFilter

public final class DepthwiseConv2dNativeBackpropFilter

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

Nested Classes

class DepthwiseConv2dNativeBackpropFilter.Options Optional attributes for DepthwiseConv2dNativeBackpropFilter

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output <T>
asOutput ()
Returns the symbolic handle of the tensor.
static <T extends TNumber > DepthwiseConv2dNativeBackpropFilter <T>
create ( Scope scope, Operand <T> input, Operand < TInt32 > filterSizes, Operand <T> outBackprop, List<Long> strides, String padding, Options... options)
Factory method to create a class wrapping a new DepthwiseConv2dNativeBackpropFilter operation.
static DepthwiseConv2dNativeBackpropFilter.Options
dataFormat (String dataFormat)
static DepthwiseConv2dNativeBackpropFilter.Options
dilations (List<Long> dilations)
static DepthwiseConv2dNativeBackpropFilter.Options
explicitPaddings (List<Long> explicitPaddings)
Output <T>
output ()
4-D with shape `[filter_height, filter_width, in_channels, out_channels]`.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "DepthwiseConv2dNativeBackpropFilter"

Public Methods

public Output <T> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static DepthwiseConv2dNativeBackpropFilter <T> create ( Scope scope, Operand <T> input, Operand < TInt32 > filterSizes, Operand <T> outBackprop, List<Long> strides, String padding, Options... options)

Factory method to create a class wrapping a new DepthwiseConv2dNativeBackpropFilter operation.

Parameters
scope current scope
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.
filterSizes An integer vector representing the tensor shape of `filter`, where `filter` is a 4-D `[filter_height, filter_width, in_channels, depthwise_multiplier]` tensor.
outBackprop 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.
options carries optional attributes values
Returns
  • a new instance of DepthwiseConv2dNativeBackpropFilter

public static DepthwiseConv2dNativeBackpropFilter.Options dataFormat (String dataFormat)

Parameters
dataFormat 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].

public static DepthwiseConv2dNativeBackpropFilter.Options dilations (List<Long> dilations)

Parameters
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.

public static DepthwiseConv2dNativeBackpropFilter.Options explicitPaddings (List<Long> explicitPaddings)

public Output <T> output ()

4-D with shape `[filter_height, filter_width, in_channels, out_channels]`. Gradient w.r.t. the `filter` input of the convolution.