Glorot uniform initializer, also called Xavier uniform initializer.
It draws samples from a uniform distribution within [-limit, limit]
where limit is sqrt(6 / (fan_in + fan_out))
where fan_in is the number of input units in the weight tensor
and fan_out is the number of output units in the weight tensor
Glorot uniform initializer, also called Xavier uniform initializer. It draws samples from a uniform distribution within [-limit, limit] where
limitissqrt(6 / (fan_in + fan_out))wherefan_inis the number of input units in the weight tensor andfan_outis the number of output units in the weight tensorReference: Glorot & Bengio, AISTATS 2010 http://jmlr.org/proceedings/papers/v9/glorot10a/glorot10a.pdf.