please, explain me about transforms.Normalize; I put in my code this transforms.Normalize([0.4161,],[0.1688,]) to image type gray and image type RGB transforms.Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225])
and
transforms.Normalize(
mean=[-0.485/0.229, -0.456/0.224, -0.406/0.225], std=[1/0.229, 1/0.224, 1/0.225]
transform.Normalize normalizes the input tensor by subtracting the specified mean and dividing by the std to create a tensor with zero mean and unit variance.
The docs also give the formula for it.
The posted values are the mean and std of ImageNet, which can often be reused.
You could also calculate these values for your training dataset as e.g. explained here.