V-JEPA 2
V-JEPA 2 produces video embeddings and supports training an attentive classification probe.
- Task
- embeddings, classification
- Ukuran
- l256, h256, g256, g384 at 256 to 384 px
- Instalasi
pip install libreyolo- Tier dukungan
- Didukung, sejak v1.6.0. Model pendukung yang dapat dilatih: CI dijaga tetap lulus, fitur ditambahkan saat ada kesempatan.
- Lisensi
- Kode MIT, bobot MIT; Apache-2.0 for giant encoder artifacts. Penggunaan komersial
Install
pip install "libreyolo"Predict
from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreVJEPA2l256-embed.pt", device="cpu")result = model(SAMPLE_IMAGE)print(result.embeddings)tokens = model.embed_tokens(SAMPLE_IMAGE)print(tokens.shape)A still image is promoted to a clip. embed_tokens() returns (B, T, H, W, D) tokens; the public embedding normalizes their mean. Exported clip graphs require direct five-dimensional runtime input.
Train
Only the attentive probe and linear classifier train; the encoder stays frozen. Use the classification task and a video-manifest dataset. Defaults are 10 epochs, batch 2, learning rate 0.001 and workers 0. Full encoder fine-tuning and pretraining are not supported.
Dataset setup describes the required training data.
from libreyolo import LibreYOLO model = LibreYOLO("LibreVJEPA2l256-cls-ssv2.pt", device="cpu")# Replace with your video dataset YAML (train/val manifests of '<video-path> <class-id>' lines).model.train(data="path/to/your/video_dataset.yaml", epochs=1, device="cpu", workers=0)Validate
from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreVJEPA2l256-cls-ssv2.pt", device="cpu")# Replace with your video dataset YAML; val() reads its val manifest of '<video-path> <class-id>' lines.metrics = model.val(data="path/to/your/video_dataset.yaml", workers=0)print(metrics)Use the dataset format for this task. Validation explains the dataset requirements and returned metrics.
Export
| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Embeddings | Embeddings to ONNX: didukung | Embeddings to TorchScript: didukung | Embeddings to ExecuTorch: didukung | Embeddings to TensorRT: didukung | Embeddings to OpenVINO: didukung | Embeddings to Paddle: tidak didukung | Embeddings to MNN: tidak didukung | Embeddings to RKNN: tidak didukung | Embeddings to ncnn: tidak didukung | Embeddings to TFLite: tidak didukung | Embeddings to CoreML: tidak didukung | Embeddings to Core AI: tidak didukung |
| Classification | Classification to ONNX: didukung | Classification to TorchScript: didukung | Classification to ExecuTorch: didukung | Classification to TensorRT: didukung | Classification to OpenVINO: didukung | Classification to Paddle: tidak didukung | Classification to MNN: tidak didukung | Classification to RKNN: tidak didukung | Classification to ncnn: tidak didukung | Classification to TFLite: tidak didukung | Classification to CoreML: tidak didukung | Classification to Core AI: tidak didukung |
from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreVJEPA2l256-embed.pt", device="cpu")model.export(format="onnx")Export setup lists format dependencies and loading exported artifacts.
Checkpoints
| Berkas | Lisensi bobot |
|---|---|
| Embeddings | |
| LibreVJEPA2h256-embed.pt | mit |
| LibreVJEPA2l256-embed.pt | mit |
| LibreVJEPA2g384-embed.pt | apache-2.0 |
| LibreVJEPA2g256-embed.pt | apache-2.0 |
| Classification | |
| LibreVJEPA2l256-cls-ssv2.pt | mit |
| LibreVJEPA2l256-cls-diving48.pt | mit |
| LibreVJEPA2g384-cls-diving48.pt | mit |
| LibreVJEPA2g384-cls-ssv2.pt | mit |
Setiap berkas di atas saat ini tersedia di organisasi LibreYOLO dan diunduh saat pertama kali digunakan.
Licensing
Periksa lisensi di repositori Hugging Face untuk bobot tertentu yang diunduh. Setiap checkpoint di organisasi LibreYOLO memiliki lisensi, dan lisensinya tidak selalu sama dalam satu family. Repositori tersebut adalah sumber resmi. Ringkasan di bawah menjelaskan ketentuan yang berlaku saat halaman ini terakhir diverifikasi.
Ini adalah deskripsi lisensi yang terlibat, bukan nasihat hukum. Jika jawabannya penting secara komersial, baca sendiri lisensinya dan mintalah nasihat dari penasihat hukum Anda.
- Karya asli
- V-JEPA 2, Meta AI
- Lisensi upstream
- MIT; Apache-2.0 for giant encoder artifacts
- Sumber upstream
- github.com/facebookresearch/vjepa2
- Kode LibreYOLO
- MIT
- Bobot
- MIT; Apache-2.0 for giant encoder artifacts, dipublikasikan ulang di huggingface.co/LibreYOLO
- Interpretasi
- Licenses differ by artifact: the two giant encoder artifacts are Apache-2.0; the other mirrored encoders and classification probes are MIT.
