@Name(value="caffe::EuclideanLossLayer<float>") @NoOffset @Properties(inherit=caffe.class) public class FloatEuclideanLossLayer extends FloatLossLayer
E = \frac{1}{2N} \sum\limits_{n=1}^N \left| \left| \hat{y}_n - y_n
\right| \right|_2^2
for real-valued regression tasks.Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
FloatEuclideanLossLayer(LayerParameter param) |
FloatEuclideanLossLayer(Pointer p)
Pointer cast constructor.
|
Modifier and Type | Method and Description |
---|---|
boolean |
AllowForceBackward(int bottom_index)
Unlike most loss layers, in the EuclideanLossLayer we can backpropagate
to both inputs -- override to return true and always allow force_backward.
|
protected void |
Backward_cpu(FloatBlobVector top,
BoolVector propagate_down,
FloatBlobVector bottom) |
protected void |
Backward_gpu(FloatBlobVector top,
BoolVector propagate_down,
FloatBlobVector bottom) |
protected void |
Forward_cpu(FloatBlobVector bottom,
FloatBlobVector top) |
protected void |
Forward_gpu(FloatBlobVector bottom,
FloatBlobVector top) |
void |
Reshape(FloatBlobVector bottom,
FloatBlobVector top)
\brief Adjust the shapes of top blobs and internal buffers to accommodate
the shapes of the bottom blobs.
|
BytePointer |
type()
\brief Returns the layer type.
|
AutoTopBlobs, ExactNumBottomBlobs, ExactNumTopBlobs, LayerSetUp
Backward, blobs, CheckBlobCounts, EqualNumBottomTopBlobs, Forward, layer_param, loss, MaxBottomBlobs, MaxTopBlobs, MinBottomBlobs, MinTopBlobs, param_propagate_down, set_loss, set_param_propagate_down, SetUp, ToProto
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 FloatEuclideanLossLayer(Pointer p)
Pointer(Pointer)
.public FloatEuclideanLossLayer(@Const @ByRef LayerParameter param)
@Virtual public void Reshape(@Const @ByRef FloatBlobVector bottom, @Const @ByRef FloatBlobVector top)
FloatLayer
Reshape
in class FloatLossLayer
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}) @Cast(value="const char*") public BytePointer type()
FloatLayer
type
in class FloatLayer
@Virtual @Cast(value="bool") @Const(value={false,false,true}) public boolean AllowForceBackward(@Const int bottom_index)
AllowForceBackward
in class FloatLossLayer
@Virtual protected void Forward_cpu(@Const @ByRef FloatBlobVector bottom, @Const @ByRef FloatBlobVector top)
Forward_cpu
in class FloatLayer
@Virtual protected void Forward_gpu(@Const @ByRef FloatBlobVector bottom, @Const @ByRef FloatBlobVector top)
Forward_gpu
in class FloatLayer
@Virtual protected void Backward_cpu(@Const @ByRef FloatBlobVector top, @Const @ByRef BoolVector propagate_down, @Const @ByRef FloatBlobVector bottom)
Backward_cpu
in class FloatLayer
@Virtual protected void Backward_gpu(@Const @ByRef FloatBlobVector top, @Const @ByRef BoolVector propagate_down, @Const @ByRef FloatBlobVector bottom)
Backward_gpu
in class FloatLayer
Copyright © 2022. All rights reserved.