MiniGPT-4
MiniGPT-4 copied to clipboard
How to preprocess IconQA for evaluation?
Describe the bug I have download the IconQA dataset through the link, but I find the way of organization of the data is different with the required. The images and annotations are scattered over many folders. How can I preprocess the dataset?
Screenshots
the organization of the dataset is like this:
+1
same question here
anybody figure out this one?