org.tensorflow.op.nn

Class Conv3dBackpropInput.Options

java.lang.Object

org.tensorflow.op.nn.Conv3dBackpropInput.Options

Enclosing class:

Conv3dBackpropInput<U extends Number>

public static class Conv3dBackpropInput.Options
extends Object

Optional attributes for Conv3dBackpropInput

Method Summary

Modifier and Type	Method and Description
Conv3dBackpropInput.Options	dataFormat(String dataFormat)
Conv3dBackpropInput.Options	dilations(List<Long> dilations)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

dataFormat

public Conv3dBackpropInput.Options dataFormat(String dataFormat)

Parameters:

dataFormat - The data format of the input and output data. With the default format "NDHWC", the data is stored in the order of: [batch, in_depth, in_height, in_width, in_channels]. Alternatively, the format could be "NCDHW", the data storage order is: [batch, in_channels, in_depth, in_height, in_width].

dilations

public Conv3dBackpropInput.Options dilations(List<Long> dilations)

Parameters:

dilations - 1-D tensor of length 5. 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.