T
- data type for resizedImages()
output@Operator(group="image") public final class QuantizedResizeBilinear<T> extends PrimitiveOp
Input images and output images must be quantized types.
Modifier and Type | Class and Description |
---|---|
static class |
QuantizedResizeBilinear.Options
Optional attributes for
QuantizedResizeBilinear |
operation
Modifier and Type | Method and Description |
---|---|
static QuantizedResizeBilinear.Options |
alignCorners(Boolean alignCorners) |
static <T> QuantizedResizeBilinear<T> |
create(Scope scope,
Operand<T> images,
Operand<Integer> size,
Operand<Float> min,
Operand<Float> max,
QuantizedResizeBilinear.Options... options)
Factory method to create a class wrapping a new QuantizedResizeBilinear operation.
|
static QuantizedResizeBilinear.Options |
halfPixelCenters(Boolean halfPixelCenters) |
Output<Float> |
outMax() |
Output<Float> |
outMin() |
Output<T> |
resizedImages()
4-D with shape
`[batch, new_height, new_width, channels]`.
|
equals, hashCode, op, toString
public static <T> QuantizedResizeBilinear<T> create(Scope scope, Operand<T> images, Operand<Integer> size, Operand<Float> min, Operand<Float> max, QuantizedResizeBilinear.Options... options)
scope
- current scopeimages
- 4-D with shape `[batch, height, width, channels]`.size
- = A 1-D int32 Tensor of 2 elements: `new_height, new_width`. The
new size for the images.min
- max
- options
- carries optional attributes valuespublic static QuantizedResizeBilinear.Options alignCorners(Boolean alignCorners)
alignCorners
- If true, the centers of the 4 corner pixels of the input and output tensors are
aligned, preserving the values at the corner pixels. Defaults to false.public static QuantizedResizeBilinear.Options halfPixelCenters(Boolean halfPixelCenters)
halfPixelCenters
- public Output<T> resizedImages()
Copyright © 2022. All rights reserved.