bytedance/OmniScient-Model
This repo contains the code for our paper Towards Open-Ended Visual Recognition with Large Language Model
Jupyter NotebookApache-2.0
Issues
- 1
Using FSDP
#5 opened by Yeon07 - 3
Replacing Sliding Window CLIP ViT feature with Dense Perpixel CLIP feature without retraining
#4 opened by PhucNDA - 1
Batch Forwarding while Testing
#3 opened by PhucNDA - 2
我觉得这篇文章特别好
#2 opened by hhaAndroid