mlboydaisuke's picture
Mirror of mlboydaisuke/VJEPA2-ViTL-SSv2-CoreAI
2dcea01 verified
|
Raw
History Blame Contribute Delete
2.3 kB
metadata
license: mit
base_model: facebook/vjepa2-vitl-fpc16-256-ssv2
tags:
  - coreai
  - apple
  - video-classification
  - v-jepa
  - world-model
  - on-device
pipeline_tag: video-classification

Mirror of mlboydaisuke/VJEPA2-ViTL-SSv2-CoreAI — the canonical repo (CoreAI Model Zoo). Updates land there first.

V-JEPA 2 (ViT-L, SSv2 action recognition) — Apple Core AI

V-JEPA 2 (Meta AI) running natively on the Apple Core AI engine — the zoo's first world model: a self-supervised video encoder that learns by predicting in representation space (JEPA), here with the Something-Something v2 action head (174 classes of physical interactions — put/lift/push/roll/cover/pretend…).

  • One bundle: ViT-L backbone (3D RoPE attention) + attentive pooler + classifier, ~375M params, fp16 ~675 MB.
  • I/O: pixel_values_videos [1,16,3,256,256] (16 frames, RGB 0..1, ImageNet mean/std) → logits [1,174] (labels.json).
  • Verified: engine vs PyTorch reference cosine 0.999996, top-5 identical; a synthetic motion probe (square moving up vs down) flips the predicted direction correctly.
  • Speed: ~150–180 ms per 16-frame clip on an M4 Max (GPU) — real-time video understanding.

Files

path what
macos/vjepa2_ssv2_fp16.aimodel fp16 bundle (macOS / JIT)
ios/vjepa2_ssv2_fp16.h18p.aimodelc iOS AOT bundle (iPhone, A18 Pro+ GPU)
macos/labels.json, ios/labels.json 174 SSv2 class names
macos/metadata.json I/O + preprocessing spec

Live demo app: coreai-video — camera → live top-3 actions. iPhone 17 Pro: ~0.34 s per 16-frame clip.

Preprocessing

Sample 16 frames uniformly from the clip, resize+center-crop to 256×256, scale to 0..1, normalize with ImageNet mean [0.485,0.456,0.406] / std [0.229,0.224,0.225], layout [1,16,3,256,256].

Credits