Generating captions with ViT and GPT2 using 🤗 Transformers | Sachin’s Blog

[utterances-bot]

Generating captions with ViT and GPT2 using 🤗 Transformers | Sachin’s Blog

Using Encoder Decoder models in HF to combine vision and text

https://sachinruk.github.io/blog/pytorch/huggingface/2021/12/28/vit-to-gpt2-encoder-decoder-model.html