search

aimagelab / show-control-and-tell

Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions. CVPR 2019
https://arxiv.org/abs/1811.10652
BSD 3-Clause "New" or "Revised" License
282 stars 62 forks source link

"test",for gaining cls_seq_test,which using det_class with caption? #19

Open jhonpj opened 4 years ago

jhonpj commented 4 years ago

dear author: for get cls_seq_test, every region corresponding to detection features,it using detection class with caption,but testing time,we will not know ground truth captions, I did not understanding. thank you, very much,for help,my mail is 2630147239@qq.com