public static class DepthwiseConv2dNativeBackpropInput.Inputs<T extends TNumber> extends RawOpInputs<DepthwiseConv2dNativeBackpropInput<T>>
Modifier and Type | Field and Description |
---|---|
String |
dataFormat
Specify the data format of the input and output data.
|
long[] |
dilations
1-D tensor of length 4.
|
long[] |
explicitPaddings
The explicitPaddings attribute
|
Operand<T> |
filter
4-D with shape
[filter_height, filter_width, in_channels, depthwise_multiplier] . |
Operand<TInt32> |
inputSizes
An integer vector representing the shape of
input , based
on data_format . |
Operand<T> |
outBackprop
4-D with shape based on
data_format . |
String |
padding
The type of padding algorithm to use.
|
long[] |
strides
The stride of the sliding window for each dimension of the input
of the convolution.
|
DataType |
T
The T attribute
|
Constructor and Description |
---|
Inputs(GraphOperation op) |
attributeMetadata, attributeNames, attributes, attributeValue, attributeValues, equals, getOutputs, hashCode, toString
public final Operand<TInt32> inputSizes
input
, based
on data_format
. For example, if data_format
is 'NHWC' then
input
is a 4-D [batch, height, width, channels]
tensor.public final Operand<T extends TNumber> filter
[filter_height, filter_width, in_channels, depthwise_multiplier]
.public final Operand<T extends TNumber> outBackprop
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.public final DataType T
public final long[] strides
public final String padding
public final long[] explicitPaddings
public final String dataFormat
public final long[] dilations
public Inputs(GraphOperation op)
Copyright © 2015–2022. All rights reserved.