vjepa2 vitl fpc64 256 EU AI Act Compliance Profile

V-JEPA 2

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository.

<img src="https://github.com/user-attachments/assets/914942d8-6a1e-409d-86ff-ff856b7346ab"> 

Installation

To run V-JEPA 2 model, ensure you have installed the latest transformers:

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

Intended Uses

V-JEPA 2 is intended to represent any video (and image) to perform video classification, retrieval, or as a video encoder for VLMs.

from transformers import AutoVideoProcessor, AutoModel

hf_repo = "facebook/vjepa2-vitl-fpc64-256"

model = AutoModel.from_pretrained(hf_repo)
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.

import torch
from torchcodec.decoders import VideoDecoder
import numpy as np

video_url = "https://huggingface.co/datasets/nateraw/kinetics-mini/resolve/main/val/archery/-Qz25rXdMjE_000014_000024.mp4"
vr = VideoDecoder(video_url)
frame_idx = np.arange(0, 64) # choosing some frames. here, you can define more complex sampling strategy
video = vr.get_frames_at(indices=frame_idx).data  # T x C x H x W
video = processor(video, return_tensors="pt").to(model.device)
with torch.no_grad():
    video_embeddings = model.get_vision_features(**video)

print(video_embeddings.shape)

To load an image, simply copy the image to the desired number of frames.

from transformers.image_utils import load_image

image = load_image("https://huggingface.co/datasets/merve/coco/resolve/main/val2017/000000000285.jpg")
pixel_values = processor

Your obligations as a vjepa2 vitl fpc64 256 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library