Closed rongliangzi closed 4 years ago
Thanks for the released code! we can see there are normalization in both train and test as follows:
transforms.Compose([ transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), ])
so why do we need normalization? how are the parameters 'mean' & 'std' calculated?
I get it. It's illustrated in pytorch tutorial as here
Thanks for the released code! we can see there are normalization in both train and test as follows:
so why do we need normalization? how are the parameters 'mean' & 'std' calculated?