org.tensorflow.op.nn

Class QuantizedConv2d.Options

java.lang.Object

org.tensorflow.op.nn.QuantizedConv2d.Options

Enclosing class:

QuantizedConv2d<V>

public static class QuantizedConv2d.Options
extends Object

Optional attributes for QuantizedConv2d

Method Summary

Modifier and Type	Method and Description
QuantizedConv2d.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

dilations

public QuantizedConv2d.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.