He normal initializer.

It draws samples from a truncated normal distribution centered on 0 with standard deviation (after truncation) given by stddev = sqrt(2 / fan_in) where fan_in is the number of input units in the weight tensor.

seed PRNG seed; see tfp.random.sanitize_seed for details. Default value: None.

init_fn A python callable which takes a shape Tensor, dtype and an optional scalar int number of batch dims and returns a randomly initialized Tensor with the specified shape and dtype.

He et al., 2015 (pdf)