Closed varunnrao closed 6 years ago
I don't know whatf filename format the abstract VQA images, but as long as you can give a unique ID to each image, it should be fine. You might have to change how the id is extracted from a filename here: https://github.com/Cyanogenoid/pytorch-vqa/blob/master/data.py#L224
In place of MSCOCO images, would the code work as is with the abstract scene images? We will place the images in the same folders as mentioned in the config.py folder.