AvgPoolGrad

public final class AvgPoolGrad

Computes gradients of the average pooling function.

Nested Classes

class AvgPoolGrad.Options Optional attributes for AvgPoolGrad

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output <T>
asOutput ()
Returns the symbolic handle of the tensor.
static <T extends TNumber > AvgPoolGrad <T>
create ( Scope scope, Operand < TInt32 > origInputShape, Operand <T> grad, List<Long> ksize, List<Long> strides, String padding, Options... options)
Factory method to create a class wrapping a new AvgPoolGrad operation.
static AvgPoolGrad.Options
dataFormat (String dataFormat)
Output <T>
output ()
4-D.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "AvgPoolGrad"

Public Methods

public Output <T> asOutput ()

Returns the symbolic handle of the 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.

public static AvgPoolGrad <T> create ( Scope scope, Operand < TInt32 > origInputShape, Operand <T> grad, List<Long> ksize, List<Long> strides, String padding, Options... options)

Factory method to create a class wrapping a new AvgPoolGrad operation.

Parameters
scope current scope
origInputShape 1-D. Shape of the original input to `avg_pool`.
grad 4-D with shape `[batch, height, width, channels]`. Gradients w.r.t. the output of `avg_pool`.
ksize The size of the sliding window for each dimension of the input.
strides The stride of the sliding window for each dimension of the input.
padding The type of padding algorithm to use.
options carries optional attributes values
Returns
  • a new instance of AvgPoolGrad

public static AvgPoolGrad.Options dataFormat (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, 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 Output <T> output ()

4-D. Gradients w.r.t. the input of `avg_pool`.