vjepa2-vitg-fpc64-384-ssv2

pip install -U git+https://github.com/huggingface/transformers

import torch
import numpy as np

from torchcodec.decoders import VideoDecoder
from transformers import AutoVideoProcessor, AutoModelForVideoClassification

device = "cuda" if torch.cuda.is_available() else "cpu"

# Load model and video preprocessor
hf_repo = "facebook/vjepa2-vitg-fpc64-384-ssv2"

model = AutoModelForVideoClassification.from_pretrained(hf_repo).to(device)
processor = AutoVideoProcessor.from_pretrained(hf_repo)

# To load a video, sample the number of frames according to the model.
# For this model, we use 64.
video_url = "https://huggingface.co/datasets/nateraw/kinetics-mini/resolve/main/val/bowling/-WH-lxmGJVY_000005_000015.mp4"
vr = VideoDecoder(video_url)
frame_idx = np.arange(0, model.config.frames_per_clip, 2) # you can define more complex sampling strategy
video = vr.get_frames_at(indices=frame_idx).data  # frames x channels x height x width

# Preprocess and run inference
inputs = processor(video, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model(**inputs)
logits = outputs.logits

print("Top 5 predicted class names:")
top5_indices = logits.topk(5).indices[0]
top5_probs = torch.softmax(logits, dim=-1).topk(5).values[0]
for idx, prob in zip(top5_indices, top5_probs):
    text_label = model.config.id2label[idx.item()]
    print(f" - {text_label}: {prob:.2f}")

Top 5 predicted class names:
 - Putting [something] onto [something]: 0.39
 - Putting [something similar to other things that are already on the table]: 0.23
 - Stacking [number of] [something]: 0.07
 - Putting [something] into [something]: 0.04
 - Putting [number of] [something] onto [something]: 0.03

@techreport{assran2025vjepa2,
  title={V-JEPA~2: Self-Supervised Video Models Enable Understanding, Prediction and Planning},
  author={Assran, Mahmoud and Bardes, Adrien and Fan, David and Garrido, Quentin and Howes, Russell and
  Komeili, Mojtaba and Muckley, Matthew and Rizvi, Ammar and Roberts, Claire and Sinha, Koustuv and Zholus, Artem and
  Arnaud, Sergio and Gejji, Abha and Martin, Ada and Robert Hogan, Francois and Dugas, Daniel and
  Bojanowski, Piotr and Khalidov, Vasil and Labatut, Patrick and Massa, Francisco and Szafraniec, Marc and
  Krishnakumar, Kapil and Li, Yong and Ma, Xiaodong and Chandar, Sarath and Meier, Franziska and LeCun, Yann and
  Rabbat, Michael and Ballas, Nicolas},
  institution={FAIR at Meta},
  year={2025}
}