End-to-End Fine-tuning OpenCLIP on around 70k Image Dataset #836
Unanswered
Researcher-DL
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi,
I would like to perform end-to-end fine-tuning on OpenCLIP using a dataset of approximately 70k images, with their corresponding captions saved within a CSV file.
What is the best and most efficient way to read the dataset for fine-tuning over a few epochs? Additionally, is there an easy way to prepare it to work well with the code in this repository?
Thanks
Beta Was this translation helpful? Give feedback.
All reactions