The code is as follows:

` import torch import numpy as np x = torch.zeros((128, 3, 32, 32)) y = np.arange(128) for i in range(len(y)): x[:].uniform_(-y[i], y[i]) `

Can the for loop be replaced with something like array slicing? Thanks

I’m not sure I understand the code correctly, since you could just use the last `y`

value via `y[-1]`

to initialize `x`

. Currently you are overwriting the previously used values in `x`

and only keep the ones from the last iteration.