RuntimeError: Number of dimensions of repeat dims can not be smaller than number of dimensions of tensor

the error occur in torch.nn.functional.instancenorm()
with mean, variance , weight, and bias having same size
I am not able to figure out what is the problem.

Could you post a minimal code snippet to reproduce this issue (including the used shapes) so that we could have a look at it, please?

hi ~
I found that running_mean/var’s shape is C, not N * C
according to the [1607.08022] Instance Normalization: The Missing Ingredient for Fast Stylization, the shape of mean/var is N *C , but for torch.nn.instancenorm ,
at::alias(running_mean).copy_(running_mean_.view({ b, c }).mean(0, false)); }
i don’t know the operation of “mean(0,false)” is use for ?
So mean, variance , weight, and bias has has same size is C .