tonytan48
tonytan48
Thanks for the prompt reply. Since the images will be resized to squared shape, is it better to crop the image to square
Hi @HobbitLong , Thank you for your great contribution in this task. I was wondering the same question with @Hiiragi0107 . It seems in a supervised contrastive mode. It is...
Hi, the frequent F1 refers to the top 10 out of 96 relations in DocRED (accounts for roughly 60%), and long-tail refers to the rest of the relations. For infer-F1,...
Hi @AlexisNvn, thank you for your interest in our work! Unfortunately, our model cannot be used to directly infer on any raw text. This is because our model is only...