Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.
raft audio-features parallel pytorch feature-extraction resnet vit optical-flow clip multi-gpu i3d s3d video-features vggish r2plus1d swin visual-features timm ig65m laion
-
Updated
Oct 26, 2024 - Python