public static class DepthwiseConv2dNativeBackpropInput.Options extends Object
DepthwiseConv2dNativeBackpropInput
Modifier and Type | Method and Description |
---|---|
DepthwiseConv2dNativeBackpropInput.Options |
dataFormat(String dataFormat)
Sets the dataFormat option.
|
DepthwiseConv2dNativeBackpropInput.Options |
dilations(List<Long> dilations)
Sets the dilations option.
|
DepthwiseConv2dNativeBackpropInput.Options |
dilations(Long... dilations)
Sets the dilations option.
|
DepthwiseConv2dNativeBackpropInput.Options |
explicitPaddings(List<Long> explicitPaddings)
Sets the explicitPaddings option.
|
DepthwiseConv2dNativeBackpropInput.Options |
explicitPaddings(Long... explicitPaddings)
Sets the explicitPaddings option.
|
public DepthwiseConv2dNativeBackpropInput.Options explicitPaddings(List<Long> explicitPaddings)
explicitPaddings
- the explicitPaddings optionpublic DepthwiseConv2dNativeBackpropInput.Options explicitPaddings(Long... explicitPaddings)
explicitPaddings
- the explicitPaddings optionpublic DepthwiseConv2dNativeBackpropInput.Options dataFormat(String dataFormat)
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 DepthwiseConv2dNativeBackpropInput.Options dilations(List<Long> dilations)
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 DepthwiseConv2dNativeBackpropInput.Options dilations(Long... dilations)
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.Copyright © 2015–2022. All rights reserved.