Ahmadzei's picture
added 3 more tables for large emb model
5fa1a76
thon
from transformers import Swin2SRForImageSuperResolution, Swin2SRImageProcessor
model = Swin2SRForImageSuperResolution.from_pretrained("caidas/swin2SR-lightweight-x2-64").to(device)
processor = Swin2SRImageProcessor("caidas/swin2SR-lightweight-x2-64")
pipeline abstracts away the preprocessing and postprocessing steps that we have to do ourselves, so let's preprocess the image.