T - data type for output() output@Operator public final class MaxPoolV2<T> extends PrimitiveOp implements Operand<T>
| Modifier and Type | Class and Description |
|---|---|
static class |
MaxPoolV2.Options
Optional attributes for
MaxPoolV2 |
operation| Modifier and Type | Method and Description |
|---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T> MaxPoolV2<T> |
create(Scope scope,
Operand<T> input,
Operand<Integer> ksize,
Operand<Integer> strides,
String padding,
MaxPoolV2.Options... options)
Factory method to create a class to wrap a new MaxPoolV2 operation to the graph.
|
static MaxPoolV2.Options |
dataFormat(String dataFormat) |
Output<T> |
output()
The max pooled output tensor.
|
equals, hashCode, toStringpublic static <T> MaxPoolV2<T> create(Scope scope, Operand<T> input, Operand<Integer> ksize, Operand<Integer> strides, String padding, MaxPoolV2.Options... options)
scope - current graph scopeinput - 4-D input to pool over.ksize - The size of the window for each dimension of the input tensor.strides - The stride of the sliding window for each dimension of the
input tensor.padding - The type of padding algorithm to use.options - carries optional attributes valuespublic static MaxPoolV2.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, in_height, in_width, in_channels].
Alternatively, the format could be "NCHW", the data storage order of:
[batch, in_channels, in_height, in_width].public Output<T> asOutput()
OperandInputs 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.
asOutput in interface Operand<T>OperationBuilder.addInput(Output)Copyright © 2015–2019. All rights reserved.