Generative Image-to-Text Transformer
Jump to navigation
Jump to search
Generative Image-to-Text (GIT), first discussed in this paper, was trained on 20 million image-text pairs, and further fine-tuned on TextCaps. A robust image-to-text processor.
External Links
Please note that the content of external links are not endorsed or verified by us and can change with no notice. Use at your own risk.