Data type of the values produced by this initializer.
Data type of the values produced by this initializer. If null
, then the initializer may produce values of any
data type.
Distribution to use when sampling.
Distribution to use when sampling.
Initial variance scale.
Initial variance scale.
Generates an initial value op.
Generates an initial value op.
Data type for the output tensor.
Shape for the output tensor.
PartitionInformation object holding additional information about how the variable is
partitioned. May be null
if the variable is not partitioned.
Created op output.
ShapeMismatchException
If the initializer cannot produce a value with the requested shape.
Variance scaling mode.
Variance scaling mode.
Optional random seed, used to generate a random seed pair for the random number generator, when combined with the graph-level seed.
Optional random seed, used to generate a random seed pair for the random number generator, when combined with the graph-level seed.
Shape of the values produced by this initializer.
Shape of the values produced by this initializer. If null
, then the initializer may produce values of any
shape.
Glorot uniform initializer, also called the Xavier uniform initializer..
This initializer draws samples from a uniform distribution within
[-limit, limit]
, wherelimit
is equal tosqrt(6 / (fanIn + fanOut))
, wherefanIn
is the number of input units in the weight tensor andfanOut
is the number of output units in the weight tensor.Reference: [Understanding the difficulty of training deep feed-forward neural networks](http://jmlr.org/proceedings/papers/v9/glorot10a/glorot10a.pdf)
Optional random seed, used to generate a random seed pair for the random number generator, when combined with the graph-level seed.