CapPa - Use Vision Models as Captioners Locally
Fahd Mirza Fahd Mirza
18.3K subscribers
253 views
14

 Published On Jul 6, 2024

This video installs CapPa locally which is trained as a captioner and masked prediction on large noisy image/text dataset. It represents an alternative to building vision models through classification (on ImageNet) or contrastive learning (like CLIP).

šŸ”„ Buy Me a Coffee to support the channel: https://ko-fi.com/fahdmirza

šŸ”„ Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon:

https://bit.ly/fahd-mirza
Coupon code: FahdMirza

ā–¶ Become a Patron šŸ”„ - Ā Ā /Ā fahdmirzaĀ Ā 

#cappa

PLEASE FOLLOW ME:
ā–¶ LinkedIn: Ā Ā /Ā fahdmirzaĀ Ā 
ā–¶ YouTube: Ā Ā Ā /Ā @fahdmirzaĀ Ā 
ā–¶ Blog: https://www.fahdmirza.com

RELATED VIDEOS:

ā–¶ Resource https://github.com/borisdayma/clip-ja...

All rights reserved Ā© 2021 Fahd Mirza

show more

Share/Embed