BiAM
BiAM copied to clipboard
[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages
Hey Will you please help me with the following: 1. How can I get the "/images.csv" 2. Where to find 'full_train_partition_idxs.npy' and 'full_train_files.npy'
looks like the file has moved to your bin folder in the drive. please provide json files
Hello, I'm interested in your excellent work. I want to know **if there is difference between downloading openImages from 2017_11 folder or 2018_4 folder**? The download_images.py you provided only support...
Hi, thanks for your awesome work. In the paper, the number of unseen labels is 400. Why are there 2594 labels in the `unseen_labels.pkl` file?