@Namespace(value="tensorflow::ops::internal") @NoOffset @Properties(inherit=tensorflow.class) public class FractionalAvgPoolGrad extends Pointer
fractional_avg_pool
* out_backprop: 4-D with shape [batch, height, width, channels]
. Gradients
w.r.t. the output of fractional_avg_pool
.
* row_pooling_sequence: row pooling sequence, form pooling region with
col_pooling_sequence.
* col_pooling_sequence: column pooling sequence, form pooling region with
row_pooling sequence.
Optional attributes (see Attrs
):
* overlapping: When set to True, it means when pooling, the values at the boundary
of adjacent pooling cells are used by both cells. For example:
index 0 1 2 3 4
value 20 5 16 3 7
If the pooling sequence is [0, 2, 4], then 16, at index 2 will be used twice.
The result would be [41/3, 26/3] for fractional avg pooling.
Returns:
* Output
: 4-D. Gradients w.r.t. the input of fractional_avg_pool
.Modifier and Type | Class and Description |
---|---|
static class |
FractionalAvgPoolGrad.Attrs
Optional attribute setters for FractionalAvgPoolGrad
|
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
FractionalAvgPoolGrad(Pointer p)
Pointer cast constructor.
|
FractionalAvgPoolGrad(Scope scope,
Input orig_input_tensor_shape,
Input out_backprop,
Input row_pooling_sequence,
Input col_pooling_sequence) |
FractionalAvgPoolGrad(Scope scope,
Input orig_input_tensor_shape,
Input out_backprop,
Input row_pooling_sequence,
Input col_pooling_sequence,
FractionalAvgPoolGrad.Attrs attrs) |
Modifier and Type | Method and Description |
---|---|
Input |
asInput() |
Output |
asOutput() |
Node |
node() |
Operation |
operation() |
FractionalAvgPoolGrad |
operation(Operation setter) |
Output |
output() |
FractionalAvgPoolGrad |
output(Output setter) |
static FractionalAvgPoolGrad.Attrs |
Overlapping(boolean x) |
address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero
public FractionalAvgPoolGrad(Pointer p)
Pointer(Pointer)
.public FractionalAvgPoolGrad(@Const @ByRef Scope scope, @ByVal Input orig_input_tensor_shape, @ByVal Input out_backprop, @ByVal Input row_pooling_sequence, @ByVal Input col_pooling_sequence)
public Node node()
@ByVal public static FractionalAvgPoolGrad.Attrs Overlapping(@Cast(value="bool") boolean x)
public FractionalAvgPoolGrad operation(Operation setter)
public FractionalAvgPoolGrad output(Output setter)
Copyright © 2022. All rights reserved.