Modifier and Type | Class and Description |
---|---|
static class |
Conv2dBackpropFilter.Options
Optional attributes for
Conv2dBackpropFilter |
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> input,
Operand<Integer> filterSizes,
Operand<T> outBackprop,
List<Long> strides,
String padding,
Conv2dBackpropFilter.Options... options)
Factory method to create a class wrapping a new Conv2dBackpropFilter operation.
|
static Conv2dBackpropFilter.Options |
dataFormat(String dataFormat) |
static Conv2dBackpropFilter.Options |
dilations(List<Long> dilations) |
static Conv2dBackpropFilter.Options |
explicitPaddings(List<Long> explicitPaddings) |
Output<T> |
output()
4-D with shape
`[filter_height, filter_width, in_channels, out_channels]`.
|
static Conv2dBackpropFilter.Options |
useCudnnOnGpu(Boolean useCudnnOnGpu) |
equals, hashCode, op, toString
public static <T extends Number> Conv2dBackpropFilter<T> create(Scope scope, Operand<T> input, Operand<Integer> filterSizes, Operand<T> outBackprop, List<Long> strides, String padding, Conv2dBackpropFilter.Options... options)
scope
- current scopeinput
- 4-D with shape `[batch, in_height, in_width, in_channels]`.filterSizes
- An integer vector representing the tensor shape of `filter`,
where `filter` is a 4-D
`[filter_height, filter_width, in_channels, out_channels]` tensor.outBackprop
- 4-D with shape `[batch, out_height, out_width, out_channels]`.
Gradients w.r.t. the output of the convolution.strides
- The stride of the sliding window for each dimension of the input
of the convolution. Must be in the same order as the dimension specified with
format.padding
- The type of padding algorithm to use.options
- carries optional attributes valuespublic static Conv2dBackpropFilter.Options useCudnnOnGpu(Boolean useCudnnOnGpu)
useCudnnOnGpu
- public static Conv2dBackpropFilter.Options explicitPaddings(List<Long> explicitPaddings)
explicitPaddings
- If `padding` is `"EXPLICIT"`, the list of explicit padding amounts. For the ith
dimension, the amount of padding inserted before and after the dimension is
`explicit_paddings[2 * i]` and `explicit_paddings[2 * i + 1]`, respectively. If
`padding` is not `"EXPLICIT"`, `explicit_paddings` must be empty.public static Conv2dBackpropFilter.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 static Conv2dBackpropFilter.Options dilations(List<Long> dilations)
dilations
- 1-D tensor of length 4. The dilation factor for each dimension of
`input`. If set to k > 1, there will be k-1 skipped cells between each filter
element on that dimension. The dimension order is determined by the value of
`data_format`, see above for details. Dilations in the batch and depth
dimensions must be 1.public Output<T> output()
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.