How do I input the video? Do you have sample code?
#1
by
michaelj
- opened
I really like this model. How do I input the video? Do you have sample code? Can it understand the spatial relationships in the video, such as understanding a large indoor video and combining it with input images for indoor navigation
Check our github, we provide comprehensive examples for inference and fine-tunes
https://github.com/rhymes-ai/Aria/blob/main/inference/notebooks/04_video_understanding.ipynb