W
- data type for output()
outputpublic final class QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize<W> extends PrimitiveOp
Modifier and Type | Class and Description |
---|---|
static class |
QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options
Optional attributes for
QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize |
operation
Modifier and Type | Method and Description |
---|---|
static <W,T,U,V> QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize<W> |
create(Scope scope,
Operand<T> input,
Operand<U> filter,
Operand<V> bias,
Operand<Float> minInput,
Operand<Float> maxInput,
Operand<Float> minFilter,
Operand<Float> maxFilter,
Operand<Float> minFreezedOutput,
Operand<Float> maxFreezedOutput,
Class<W> outType,
List<Long> strides,
String padding,
QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options... options)
Factory method to create a class wrapping a new QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize operation.
|
static QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options |
dilations(List<Long> dilations) |
Output<Float> |
maxOutput()
The float value that the maximum quantized output value represents.
|
Output<Float> |
minOutput()
The float value that the minimum quantized output value represents.
|
Output<W> |
output()
The output tensor.
|
equals, hashCode, op, toString
public static <W,T,U,V> QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize<W> create(Scope scope, Operand<T> input, Operand<U> filter, Operand<V> bias, Operand<Float> minInput, Operand<Float> maxInput, Operand<Float> minFilter, Operand<Float> maxFilter, Operand<Float> minFreezedOutput, Operand<Float> maxFreezedOutput, Class<W> outType, List<Long> strides, String padding, QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options... options)
scope
- current scopeinput
- The original input tensor.filter
- The original filter tensor.bias
- The original bias tensor.minInput
- The float value that the minimum quantized input value represents.maxInput
- The float value that the maximum quantized input value represents.minFilter
- The float value that the minimum quantized filter value represents.maxFilter
- The float value that the maximum quantized filter value represents.minFreezedOutput
- The minimum float value of the output tensor.maxFreezedOutput
- The maximum float value of the output tensor.outType
- The type of the output.strides
- List of stride values.padding
- options
- carries optional attributes valuespublic static QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options dilations(List<Long> dilations)
dilations
- List of dilation values.public Output<Float> minOutput()
Copyright © 2022. All rights reserved.