Package org.tensorflow.op.nn

Class DepthwiseConv2dNative<T extends java.lang.Number>

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.nn.DepthwiseConv2dNative<T>

Type Parameters:

T - data type for output() output

All Implemented Interfaces:

Op, Operand<T>

@Operator(group="nn")
public final class DepthwiseConv2dNative<T extends java.lang.Number>
extends PrimitiveOp
implements Operand<T>

Computes a 2-D depthwise convolution given 4-D `input` and `filter` tensors.

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]`.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	DepthwiseConv2dNative.Options	Optional attributes for DepthwiseConv2dNative

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
Output<T>	asOutput()	Returns the symbolic handle of a tensor.
static <T extends java.lang.Number> DepthwiseConv2dNative<T>	create(Scope scope, Operand<T> input, Operand<T> filter, java.util.List<java.lang.Long> strides, java.lang.String padding, DepthwiseConv2dNative.Options... options)	Factory method to create a class to wrap a new DepthwiseConv2dNative operation to the graph.
static DepthwiseConv2dNative.Options	dataFormat(java.lang.String dataFormat)
static DepthwiseConv2dNative.Options	dilations(java.util.List<java.lang.Long> dilations)
Output<T>	output()

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

public static <T extends java.lang.Number> DepthwiseConv2dNative<T> create(Scope scope,
                                                                           Operand<T> input,
                                                                           Operand<T> filter,
                                                                           java.util.List<java.lang.Long> strides,
                                                                           java.lang.String padding,
                                                                           DepthwiseConv2dNative.Options... options)

Factory method to create a class to wrap a new DepthwiseConv2dNative operation to the graph.

Parameters:

scope - current graph scope

input -

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 values

Returns:

a new instance of DepthwiseConv2dNative

dataFormat

public static DepthwiseConv2dNative.Options dataFormat(java.lang.String dataFormat)

Parameters:

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].

dilations

public static DepthwiseConv2dNative.Options dilations(java.util.List<java.lang.Long> dilations)

Parameters:

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.

output

public Output<T> output()

asOutput

public Output<T> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a tensor.

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.

Specified by:

asOutput in interface Operand<T extends java.lang.Number>

See Also:

OperationBuilder.addInput(Output)