Defined in File init.h
Tensor torch::nn::init::xavier_uniform_(Tensor tensor, double gain = 1.0)¶
Fills the input
with values according to the method described in “Understanding the difficulty of training deep feedforward
neural networks” - Glorot, X.
& Bengio, Y. (2010), using a uniform distribution. Values are scaled by the
gainparameter No gradient will be recorded for this operation.