Hello guys.
In a transformation of a Pil Image (1200x1200) to a Tensor like this.
T.Compose([T.Resize((224, 224), Image.ANTIALIAS),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
has Image.ANTIALIAS sense ? as far as I know, antialias flag (in resize) is True by default if the Image is PIL
I usually use something like InterpolationMode.BILINEAR or InterpolationMode.BICUBIC lit this:
T.Compose([T.Resize((224, 224), InterpolationMode.BILINEAR),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
but sometimes, I see people using Image.ANTIALIAS and that confuses me.
Is there any reason for using Image.ANTIALIAS?.
Thanks