yashkant / sam-textvqa

Official code for paper "Spatially Aware Multimodal Transformers for TextVQA" published at ECCV, 2020.

Home Page:https://yashkant.github.io/projects/sam-textvqa

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Visualization results from prediction

HenryJunW opened this issue · comments

Hello, good work, thanks for open source your code! Right now I want to visualize the question, image and predicted answer. I am wondering whether there is any function/demo file which takes in an image and gives out the prediction for that image. Thanks.

Hi @HenryJunW,

Thank you for your interest in our work!

I am afraid I do not have any visualization code in this repository, but you can build a simple HTML file using the predictions of SAM that I have shared here.

Thanks for your reply!