MaxPoolGrad

public final class MaxPoolGrad

Computes gradients of the maxpooling function.

Nested Classes

class MaxPoolGrad.Options Optional attributes for MaxPoolGrad

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 > MaxPoolGrad <T>
create ( Scope scope, Operand <T> origInput, Operand <T> origOutput, Operand <T> grad, Operand < TInt32 > ksize, Operand < TInt32 > strides, String padding, Options... options)
Factory method to create a class wrapping a new MaxPoolGrad operation.
static MaxPoolGrad.Options
dataFormat (String dataFormat)
Output <T>
output ()
Gradients w.r.t.

Inherited Methods

Constants

public static final String OP_NAME

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

Constant Value: "MaxPoolGradV2"

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 MaxPoolGrad <T> create ( Scope scope, Operand <T> origInput, Operand <T> origOutput, Operand <T> grad, Operand < TInt32 > ksize, Operand < TInt32 > strides, String padding, Options... options)

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

Parameters
scope current scope
origInput The original input tensor.
origOutput The original output tensor.
grad 4-D. Gradients w.r.t. the output of `max_pool`.
ksize The size of the window for each dimension of the input tensor.
strides The stride of the sliding window for each dimension of the input tensor.
padding The type of padding algorithm to use.
options carries optional attributes values
Returns
  • a new instance of MaxPoolGrad

public static MaxPoolGrad.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 ()

Gradients w.r.t. the input to `max_pool`.