Hugging Face's logo

nlpconnect
/
vit-gpt2-image-captioning

Image-to-Text
Transformers
PyTorch
vision-encoder-decoder
image-text-to-text
image-captioning
Inference Endpoints
Model card Files
xet
Community
43

Any good?

#1
by Nabil - opened
Discussion
Nabil

Hi,

how accurate and how fast does it generate the captions.

Thank you

ankur310794
 NLP Connect org

This image captioning model was trained by @ydshieh in flax, this is the PyTorch version of https://huggingface.co/ydshieh/vit-gpt2-coco-en-ckpts model.

Please see this: https://huggingface.co/ydshieh/vit-gpt2-coco-en-ckpts/tensorboard

ankur310794
 NLP Connect org

https://ankur3107.github.io/blogs/the-illustrated-image-captioning-using-transformers

ankur310794 changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment