After downloading the test dataset from the official website, there is actually 22G of the data.
Is the 1204 images selected for the validation set specific? Is that randomly chosen or others?
If there is no test dataset for val, here should have some changes:
from:
if split in ['train', 'test']:
self.img_pth = os.path.join(root, split, 'canon')
to:
if split in ['train', 'test']:
self.img_pth = os.path.join(root, 'train', 'canon')
Hi! Pokaaa, I can't download the synthetic burst dataset on the official web, due to the 404 error on the website, could you please offer me the original dataset with Google drive or some way? Thank you!!!!
After downloading the test dataset from the official website, there is actually 22G of the data. Is the 1204 images selected for the validation set specific? Is that randomly chosen or others?
If there is no test dataset for val, here should have some changes: from:
to:
Am I right?