public final class
QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize
Computes quantized depthwise Conv2D with Bias, Relu and Requantize.
Nested Classes
| class | QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options | Optional attributes for QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize
|
|
Constants
| String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
| static <W extends TType> QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize<W> |
create(Scope scope, Operand<? extends TType> input, Operand<? extends TType> filter, Operand<? extends TType> bias, Operand<TFloat32> minInput, Operand<TFloat32> maxInput, Operand<TFloat32> minFilter, Operand<TFloat32> maxFilter, Operand<TFloat32> minFreezedOutput, Operand<TFloat32> maxFreezedOutput, Class<W> outType, List<Long> strides, String padding, Options... options)
Factory method to create a class wrapping a new QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize operation.
|
| static QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options |
dilations(List<Long> dilations)
|
| Output<TFloat32> |
maxOutput()
The float value that the maximum quantized output value represents.
|
| Output<TFloat32> |
minOutput()
The float value that the minimum quantized output value represents.
|
| Output<W> |
output()
The output tensor.
|
| static QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options |
paddingList(List<Long> paddingList)
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Constant Value:
"QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize"
Public Methods
public static QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize<W> create (Scope scope, Operand<? extends TType> input, Operand<? extends TType> filter, Operand<? extends TType> bias, Operand<TFloat32> minInput, Operand<TFloat32> maxInput, Operand<TFloat32> minFilter, Operand<TFloat32> maxFilter, Operand<TFloat32> minFreezedOutput, Operand<TFloat32> maxFreezedOutput, Class<W> outType, List<Long> strides, String padding, Options... options)
Factory method to create a class wrapping a new QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize operation.
Parameters
| scope | current scope |
|---|---|
| input | 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. |
| options | carries optional attributes values |
Returns
- a new instance of QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize
public static QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize.Options dilations (List<Long> dilations)
Parameters
| dilations | List of dilation values. |
|---|
public Output<TFloat32> maxOutput ()
The float value that the maximum quantized output value represents.
public Output<TFloat32> minOutput ()
The float value that the minimum quantized output value represents.