HashNet
HashNet copied to clipboard
question on nuswide dataset
Hi authors, in the paper, you mention that nuswide "use the subset of 195,834 images that are associated with the 21 most frequent concepts", but i saw vector with size of 81 in "data/nuswide_81/train.txt", may I know where do you filter the data? Or you are just using the data specified in those txt files? How about data without labels (vector with all 0s)?