@Name(value="caffe::XavierFiller<float>") @Properties(inherit=caffe.class) public class FloatXavierFiller extends FloatFiller
x \sim U(-a, +a) where a is
set inversely proportional to number of incoming nodes, outgoing
nodes, or their average.
A Filler based on the paper [Bengio and Glorot 2010]: Understanding
the difficulty of training deep feedforward neuralnetworks.
It fills the incoming matrix by randomly sampling uniform data from [-scale,
scale] where scale = sqrt(3 / n) where n is the fan_in, fan_out, or their
average, depending on the variance_norm option. You should make sure the
input blob has shape (num, a, b, c) where a * b * c = fan_in and num * b * c
= fan_out. Note that this is currently not the case for inner product layers.
TODO(dox): make notation in above comment consistent with rest & use LaTeX.Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter| Constructor and Description |
|---|
FloatXavierFiller(FillerParameter param) |
FloatXavierFiller(Pointer p)
Pointer cast constructor.
|
| Modifier and Type | Method and Description |
|---|---|
void |
Fill(FloatBlob blob) |
address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, hashCode, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, parseBytes, physicalBytes, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, toString, totalBytes, totalPhysicalBytes, withDeallocator, zeropublic FloatXavierFiller(Pointer p)
Pointer.Pointer(Pointer).public FloatXavierFiller(@Const @ByRef FillerParameter param)
public void Fill(FloatBlob blob)
Fill in class FloatFillerCopyright © 2019. All rights reserved.