https://github.com/v-iashin/video_features

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.
https://github.com/v-iashin/video_features

audio-features clip feature-extraction i3d ig65m laion multi-gpu optical-flow parallel pytorch r2plus1d raft resnet s3d swin timm vggish video-features visual-features vit

Last synced: about 22 hours ago
JSON representation

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.

• Host: GitHub
• URL: https://github.com/v-iashin/video_features
• Owner: v-iashin
• License: mit
• Created: 2020-06-01T17:57:03.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2024-09-12T08:08:58.000Z (about 2 months ago)
• Last Synced: 2024-09-12T18:34:17.829Z (about 2 months ago)
• Topics: audio-features, clip, feature-extraction, i3d, ig65m, laion, multi-gpu, optical-flow, parallel, pytorch, r2plus1d, raft, resnet, s3d, swin, timm, vggish, video-features, visual-features, vit
• Language: Python
• Homepage: https://v-iashin.github.io/video_features
• Size: 282 MB
• Stars: 497
• Watchers: 6
• Forks: 94
• Open Issues: 23
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project