pytorch-fid
pytorch-fid copied to clipboard
Resize Images at Read in (imread)
Hey there, I ran into problems as my images are of variable size (couldn't convert the list read-in to np.array). Does it make sense to consider resizing images in imread? Image.open(filename).resize((299, 299)) Best, Mike
I've also encounted this issue, my solution is to transform before dataloader:
dataset = ImagePathDataset(files,
transforms=TF.Compose([
TF.Resize((299,299)),
TF.ToTensor(),
]))
Thank you for the solution. Here is the reference architecture of the InceptionV3 model
I observe that such resize operation would change the FID score significantly.