T
- data type for output()
output@Operator(group="nn") public final class DepthwiseConv2dNative<T extends Number> extends PrimitiveOp implements Operand<T>
Given an input tensor of shape `[batch, in_height, in_width, in_channels]` and a filter / kernel tensor of shape `[filter_height, filter_width, in_channels, channel_multiplier]`, containing `in_channels` convolutional filters of depth 1, `depthwise_conv2d` applies a different filter to each input channel (expanding from 1 channel to `channel_multiplier` channels for each), then concatenates the results together. Thus, the output has `in_channels * channel_multiplier` channels.
for k in 0..in_channels-1
for q in 0..channel_multiplier-1
output[b, i, j, k * channel_multiplier + q] =
sum_{di, dj} input[b, strides[1] * i + di, strides[2] * j + dj, k] *
filter[di, dj, k, q]
Must have `strides[0] = strides[3] = 1`. For the most common case of the same
horizontal and vertices strides, `strides = [1, stride, stride, 1]`.Modifier and Type | Class and Description |
---|---|
static class |
DepthwiseConv2dNative.Options
Optional attributes for
DepthwiseConv2dNative |
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<T> filter,
List<Long> strides,
String padding,
DepthwiseConv2dNative.Options... options)
Factory method to create a class wrapping a new DepthwiseConv2dNative operation.
|
static DepthwiseConv2dNative.Options |
dataFormat(String dataFormat) |
static DepthwiseConv2dNative.Options |
dilations(List<Long> dilations) |
Output<T> |
output() |
equals, hashCode, op, toString
public static <T extends Number> DepthwiseConv2dNative<T> create(Scope scope, Operand<T> input, Operand<T> filter, List<Long> strides, String padding, DepthwiseConv2dNative.Options... options)
scope
- current scopeinput
- filter
- strides
- 1-D of length 4. The stride of the sliding window for each dimension
of `input`.padding
- The type of padding algorithm to use.options
- carries optional attributes valuespublic static DepthwiseConv2dNative.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, height, width, channels].
Alternatively, the format could be "NCHW", the data storage order of:
[batch, channels, height, width].public static DepthwiseConv2dNative.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> 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.