ASL
ASL copied to clipboard
Maybe a Bug
In train.py, between line 54 and 69, https://github.com/Alibaba-MIIL/ASL/blob/7068ff007ac5f56a0ae1794b61a7571c3e4561ec/train.py#L54-L69
It says that
#normalize, # no need, toTensor does normalization
I have different thought. To Tensor scales images to (0, 1) while normalization to (-1, 1). This should be different.
I do not test for this. Please Check it.
Thank you. :)
And another question,
If so, why you guys don't use normalization?
The reason ask this is that my f1-score shows 10% differences at most when I use normalization with your code with ResNet50