@Name(value="caffe::LossLayer<double>") @Properties(inherit=caffe.class) public class DoubleLossLayer extends DoubleLayer
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
DoubleLossLayer(LayerParameter param) |
DoubleLossLayer(Pointer p)
Pointer cast constructor.
|
Modifier and Type | Method and Description |
---|---|
boolean |
AllowForceBackward(int bottom_index)
We usually cannot backpropagate to the labels; ignore force_backward for
these inputs.
|
boolean |
AutoTopBlobs()
\brief For convenience and backwards compatibility, instruct the Net to
automatically allocate a single top Blob for LossLayers, into which
they output their singleton loss, (even if the user didn't specify
one in the prototxt, etc.).
|
int |
ExactNumBottomBlobs()
\brief Returns the exact number of bottom blobs required by the layer,
or -1 if no exact number is required.
|
int |
ExactNumTopBlobs()
\brief Returns the exact number of top blobs required by the layer,
or -1 if no exact number is required.
|
void |
LayerSetUp(DoubleBlobVector bottom,
DoubleBlobVector top)
\brief Does layer-specific setup: your layer should implement this function
as well as Reshape.
|
void |
Reshape(DoubleBlobVector bottom,
DoubleBlobVector top)
\brief Adjust the shapes of top blobs and internal buffers to accommodate
the shapes of the bottom blobs.
|
Backward_cpu, Backward_gpu, Backward, blobs, CheckBlobCounts, EqualNumBottomTopBlobs, Forward_cpu, Forward_gpu, Forward, layer_param, loss, MaxBottomBlobs, MaxTopBlobs, MinBottomBlobs, MinTopBlobs, param_propagate_down, set_loss, set_param_propagate_down, SetUp, ToProto, type
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 DoubleLossLayer(Pointer p)
Pointer(Pointer)
.public DoubleLossLayer(@Const @ByRef LayerParameter param)
@Virtual public void LayerSetUp(@Const @ByRef DoubleBlobVector bottom, @Const @ByRef DoubleBlobVector top)
DoubleLayer
LayerSetUp
in class DoubleLayer
bottom
- the preshaped input blobs, whose data fields store the input data for
this layertop
- the allocated but unshaped output blobs
This method should do one-time layer specific setup. This includes reading
and processing relevent parameters from the layer_param_
.
Setting up the shapes of top blobs and internal buffers should be done in
Reshape
, which will be called before the forward pass to
adjust the top blob sizes.@Virtual public void Reshape(@Const @ByRef DoubleBlobVector bottom, @Const @ByRef DoubleBlobVector top)
DoubleLayer
Reshape
in class DoubleLayer
bottom
- the input blobs, with the requested input shapestop
- the top blobs, which should be reshaped as needed
This method should reshape top blobs as needed according to the shapes
of the bottom (input) blobs, as well as reshaping any internal buffers
and making any other necessary adjustments so that the layer can
accommodate the bottom blobs.@Virtual @Const(value={false,false,true}) public int ExactNumBottomBlobs()
DoubleLayer
ExactNumBottomBlobs
in class DoubleLayer
@Virtual @Cast(value="bool") @Const(value={false,false,true}) public boolean AutoTopBlobs()
AutoTopBlobs
in class DoubleLayer
@Virtual @Const(value={false,false,true}) public int ExactNumTopBlobs()
DoubleLayer
ExactNumTopBlobs
in class DoubleLayer
@Virtual @Cast(value="bool") @Const(value={false,false,true}) public boolean AllowForceBackward(@Const int bottom_index)
AllowForceBackward
in class DoubleLayer
Copyright © 2022. All rights reserved.