lyzsdbd
lyzsdbd

import torch import time from vggt.models.vggt import VGGT from vggt.utils.load_fn import load_and_preprocess_images device = "cuda" if torch.cuda.is_available() else "cpu" dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] >= 8 else torch.float16 model =...
This is my code now in eval mode. It still costs 0.79 seconds.
Thanks for your answer. I now think that VGGT is unusable on real-time embedded platforms like drones. Because I don't think Jetson Orin NX will do much better than my...