I compared 3 AI Image Caption Models - GIT vs BLIP vs ViT+GPT2 - Image-to-Text Models
Автор: 1littlecoder
Загружено: 2023-01-08
Просмотров: 13383
Описание:
I took10 different images to compare GIT, BLIP and ViT+GPT2, 3 state-of-the-art vision+language models.
GIT: A Generative Image-to-text Transformer for Vision and Language
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
ViT+GPT2 - Image Captioning using transformers
Gradio Demo by Niels Rogge
https://huggingface.co/spaces/nielsr/...
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке: