nlpconnect
/

vit-gpt2-image-captioning

vision-encoder-decoder

image-text-to-text

image-captioning

Model card Files Files and versions

How to train and fine tune this model on a new dataset

#2

by zahram - opened Jun 26, 2022

I am a keras developer, how I can I train this model on a new dataset, also can I fine tune this model. Thank You

NLP Connect org Nov 27, 2022

you may refer to this blog https://ankur3107.github.io/blogs/the-illustrated-image-captioning-using-transformers/

replace pytorch trainer with keras training from https://github.com/huggingface/transformers/blob/main/examples/tensorflow/summarization/run_summarization.py

ankur310794 changed discussion status to closed Nov 27, 2022

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment