Spaces:

yuhangzang

/

ContextDet-Demo

like 13

Paused

Demo for the paper:
Contextual Object Detection with Multimodal Large Language Models
https://arxiv.org/abs/2305.18279
https://github.com/yuhangzang/ContextDET

This project heavily relies on large language models and necessitates a GPU with a minimum of 30GB RAM, such as the T4 medium. Currently, I am personally funding the expenses associated with this project. However, I would greatly appreciate it if HuggingFace could provide support by either covering the costs or offering a discount for the required GPU resources. Thanks.