torch.Tensor.random_#

Tensor.random_(from=0,to=None,*,generator=None)→Tensor#

Fillsself tensor with numbers sampled from the discrete uniformdistribution over[from,to-1]. If not specified, the values are usuallyonly bounded byself tensor’s data type. However, for floating pointtypes, if unspecified, range will be[0,2^mantissa] to ensure that everyvalue is representable. For example,torch.tensor(1, dtype=torch.double).random_()will be uniform in[0,2^53].