LAPA
Collection
LAPA (Look Around and Pay Attention): multi-camera point tracking. Contains pretrained models for TAPVid-3D-MC and PointOdyssey-MC and LAPA-Joint • 4 items • Updated
LAPA
Pretrained weights for LAPA (Look Around and Pay Attention) on Joint.
Load
import torch
from lapa.models.lapa import LAPA
ckpt = torch.load('lapa.pt', map_location='cpu')
model = LAPA()
model.load_state_dict(ckpt['model'])
model.eval()
Code: https://github.com/ostadabbas/Look-Around-and-Pay-Attention-LAPA-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support