@Name(value="caffe::MSRAFiller<float>") @Properties(inherit=caffe.class) public class FloatMSRAFiller extends FloatFiller
x \sim N(0, \sigma^2)
where
\sigma^2
is set inversely proportional to number of incoming
nodes, outgoing nodes, or their average.
A Filler based on the paper [He, Zhang, Ren and Sun 2015]: Specifically
accounts for ReLU nonlinearities.
Aside: for another perspective on the scaling factor, see the derivation of
[Saxe, McClelland, and Ganguli 2013 (v3)].
It fills the incoming matrix by randomly sampling Gaussian data with std =
sqrt(2 / 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.Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter
Constructor and Description |
---|
FloatMSRAFiller(FillerParameter param) |
FloatMSRAFiller(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, 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 FloatMSRAFiller(Pointer p)
Pointer(Pointer)
.public FloatMSRAFiller(@Const @ByRef FillerParameter param)
public void Fill(FloatBlob blob)
Fill
in class FloatFiller
Copyright © 2022. All rights reserved.