Preprocess RaFD dataset about stargan

[Fairydetail]

Could you please share me with the RaFD datasets? Because I had apply it in the official website for several days, but I don't receive an apply yet.Thanks a lot! @Sampson-Lee

[Sampson-Lee]

Hi, @Fairydetail
I am sorry to tell you that I can not share the RaFD because of the agreement. I think you can get an official permission after several days, as I had waited about 15 days. Good luck.

[Fairydetail]

I have the same problem with you. So would you mind to tell me the whether it works to crop like that. @Sampson-Lee

[Sampson-Lee]

@Fairydetail I think the results are similar, although I crop in different methods

[AdarshMJ]

While training with RaFD dataset, should I also make an attribute.txt file like that of Celeb dataset? Or only train with images?

[iamzhangyunlu]

While training with RaFD dataset, should I also make an attribute.txt file like that of Celeb dataset? Or only train with images?

same problem with you, so how do you deal with the RaFD datasets?

[cy19980615]

Hi, @yunjey
I am confused about the method of preprocessing RaFD, where the download images have initial size 618 x 1024. If I crop the images to 256 x 256, some images became partial absent, especially when the camera angle is 45 degree or 135 degree.
So I crop the initial images as follow code:
elif dataset == 'RaFD':
box = (100, 150, 600, 700)
if mode == 'train':
transform = transforms.Compose([
transforms.Lambda(lambda x: x.crop(box)),
transforms.Resize(image_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
else:
transform = transforms.Compose([
transforms.Lambda(lambda x: x.crop(box)),
transforms.Resize(image_size),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
dataset = ImageFolder(image_path, transform)

And I get some samples like
But I am not sure whether the method is right, could you help me? Thanks in advance.

hello could you share me with the RaFD dataset by mailbox：[email protected] i am Anxious to do graduation design for undergraduates，thanks very much！！！