Closed YIN95 closed 1 year ago
Hi @YIN95! You are absolutely right.
Assuming 0.5
is the true standard deviation of cifar10
, the value of data_std
should be 1
. Thanks for pointing that out!
Hi @YIN95! You are absolutely right.
Assuming
0.5
is the true standard deviation ofcifar10
, the value ofdata_std
should be1
. Thanks for pointing that out!
However, in openai's official code, they also normalize the images to [-1, 1], but the sigma_data=0.5.
Ah I see. data_std
is the standard deviation of cifar10
AFTER [-1, 1]
normalization. The standard deviation of cifar10
before normalization is about 0.25
, hence 0.5
makes sense.
Hi,
Thanks for sharing the code. I have a question about the data std, with transforms.Normalize([0.5], [0.5]), maybe the data std is 1 instead of 0.5?