operation
Modifier and Type | Method and Description |
---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T extends Number> |
create(Scope scope,
Operand<T> images,
List<Long> ksizes,
List<Long> strides,
List<Long> rates,
String padding)
Factory method to create a class wrapping a new ExtractImagePatches operation.
|
Output<T> |
patches()
4-D Tensor with shape `[batch, out_rows, out_cols, ksize_rows *
ksize_cols * depth]` containing image patches with size
`ksize_rows x ksize_cols x depth` vectorized in the "depth" dimension.
|
equals, hashCode, op, toString
public static <T extends Number> ExtractImagePatches<T> create(Scope scope, Operand<T> images, List<Long> ksizes, List<Long> strides, List<Long> rates, String padding)
scope
- current scopeimages
- 4-D Tensor with shape `[batch, in_rows, in_cols, depth]`.ksizes
- The size of the sliding window for each dimension of `images`.strides
- How far the centers of two consecutive patches are in
the images. Must be: `[1, stride_rows, stride_cols, 1]`.rates
- Must be: `[1, rate_rows, rate_cols, 1]`. This is the
input stride, specifying how far two consecutive patch samples are in the
input. Equivalent to extracting patches with
`patch_sizes_eff = patch_sizes + (patch_sizes - 1) * (rates - 1)`, followed by
subsampling them spatially by a factor of `rates`. This is equivalent to
`rate` in dilated (a.k.a. Atrous) convolutions.padding
- The type of padding algorithm to use.public Output<T> patches()
public Output<T> asOutput()
Operand
Inputs 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 extends Number>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.