Views
No views yet
1import torch
2from pytorch_i3d import InceptionI3d
3
4# Load model
5model = InceptionI3d(400, in_channels=3)
6model.load_state_dict(torch.load('weights/rgb_imagenet.pt', map_location='cpu'))
7model.replace_logits(2000)
8model.load_state_dict(torch.load('asl2000_model.pt', map_location='cpu'))
9model.eval()
10
11# Run inference on video
12# See inference.py for complete example@inproceedings{li2020word,
title={Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison},
author={Li, Dongxu and Rodriguez, Cristian and Yu, Xin and Li, Hongdong},
booktitle={The IEEE Winter Conference on Applications of Computer Vision},
pages={1459--1469},
year={2020}
}