qubvel-hf
/

vjepa2-vitl-fpc32-256-diving48

Video Classification

Model card Files Files and versions Community

qubvel-hf HF Staff commited on 14 days ago

Commit

fc02c89

·

verified ·

1 Parent(s): 83e3eb8

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -6,6 +6,8 @@ tags:
 library_name: transformers
 datasets:
 - bkprocovid19/diving48
 ---
 # V-JEPA 2
@@ -46,7 +48,7 @@ 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.
-video_url = "https://huggingface.co/qubvel-hf/vjepa2-vitl-fpc32-256-diving48/resolve/main/sample/diving.mp4"
 vr = VideoDecoder(video_url)
 frame_idx = np.arange(0, model.config.frames_per_clip, 8) # you can define more complex sampling strategy
 video = vr.get_frames_at(indices=frame_idx).data  # frames x channels x height x width

 library_name: transformers
 datasets:
 - bkprocovid19/diving48
+base_model:
+- facebook/vjepa2-vitl-fpc64-256
 ---
 # V-JEPA 2
 processor = AutoVideoProcessor.from_pretrained(hf_repo)
 # To load a video, sample the number of frames according to the model.
+video_url = "https://huggingface.co/facebook/vjepa2-vitl-fpc32-256-diving48/resolve/main/sample/diving.mp4"
 vr = VideoDecoder(video_url)
 frame_idx = np.arange(0, model.config.frames_per_clip, 8) # you can define more complex sampling strategy
 video = vr.get_frames_at(indices=frame_idx).data  # frames x channels x height x width