Closed why529913 closed 5 months ago
I used coco-stuff to train data collection 256x256 and found that the fid accuracy is low. I looked at the paper and found that the data had been filtered. Is this the reason? Can you provide the dataset in the paper?
As claimed in the README file, you can find our converted annotation file for COCO-Stuff here. We follow LAMA to deal with the original annotations.
I used coco-stuff to train data collection 256x256 and found that the fid accuracy is low. I looked at the paper and found that the data had been filtered. Is this the reason? Can you provide the dataset in the paper?