@Name(value="caffe::ThresholdLayer<float>") @NoOffset @Properties(inherit=caffe.class) public class FloatThresholdLayer extends FloatNeuronLayer
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
FloatThresholdLayer(LayerParameter param) |
FloatThresholdLayer(Pointer p)
Pointer cast constructor.
|
Modifier and Type | Method and Description |
---|---|
protected void |
Backward_cpu(FloatBlobVector top,
BoolVector propagate_down,
FloatBlobVector bottom) |
protected void |
Forward_cpu(FloatBlobVector bottom,
FloatBlobVector top) |
protected void |
Forward_gpu(FloatBlobVector bottom,
FloatBlobVector top) |
void |
LayerSetUp(FloatBlobVector bottom,
FloatBlobVector top)
\brief Does layer-specific setup: your layer should implement this function
as well as Reshape.
|
BytePointer |
type()
\brief Returns the layer type.
|
ExactNumBottomBlobs, ExactNumTopBlobs, Reshape
AllowForceBackward, AutoTopBlobs, Backward_gpu, 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 FloatThresholdLayer(Pointer p)
Pointer(Pointer)
.public FloatThresholdLayer(@Const @ByRef LayerParameter param)
param
- provides ThresholdParameter threshold_param,
with ThresholdLayer options:
- threshold (\b optional, default 0).
the threshold value t
to which the input values are compared.@Virtual public void LayerSetUp(@Const @ByRef FloatBlobVector bottom, @Const @ByRef FloatBlobVector top)
FloatLayer
LayerSetUp
in class FloatLayer
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 @Const(value={false,false,true}) @Cast(value="const char*") public BytePointer type()
FloatLayer
type
in class FloatLayer
@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
Copyright © 2022. All rights reserved.