how get the "noise image feature"?

[FutureWithoutEnding]

In the code, noise image feature is load from file.
how can i generate the noise image feature?

In the paper, said generate from a uniform distribution from 0 to 3, why 0 and 3, How get the two value? and Why use a uniform?

Can you show me some code about these?

[TysonYu]

Maybe you can search on google with "How to create random value tensor in PyTorch?"

[FutureWithoutEnding]

I know some about
noise_img_feat = np.random.uniform(0, 3, img_feat_shape)

But, I do not konw Why uniform and Why 0 ~ 3?