bottom-up-attention
bottom-up-attention copied to clipboard
Would someone please help with generating the features?
I'm wondering whether someone would please share the extracted features from dataset Flickr30k? tsv file is just fine, in a setting of MAX 36 MIN 36, which includes the io-boxes and features of dimension-2048. I tried days for fixing the environment issues but still failed.
Maybe this can help you. https://github.com/kuanghuei/SCAN. Can you download the Pretrained Model?