Instructions to use perceptuality/sam2.1-tiny-video-ort with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use perceptuality/sam2.1-tiny-video-ort with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("perceptuality/sam2.1-tiny-video-ort") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained("perceptuality/sam2.1-tiny-video-ort") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>) # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
Download vision_encoder.with_runtime_opt.ort from perceptuality/sam2.1-tiny-video-ort: direct link, hf CLI and curl.
- Browser
- Download file 223 MB
-
https://huggingface.co/perceptuality/sam2.1-tiny-video-ort/resolve/main/vision_encoder.with_runtime_opt.ort
- Command line
-
hf download hf://perceptuality/sam2.1-tiny-video-ort/vision_encoder.with_runtime_opt.ort
-
curl -L -o vision_encoder.with_runtime_opt.ort https://huggingface.co/perceptuality/sam2.1-tiny-video-ort/resolve/main/vision_encoder.with_runtime_opt.ort
223 MB
- Xet hash:
- 8fa4e308eed08b1ead55f1af7162bfdc9e2de9edcac2ae1accd5d81708c6ae1c
- Size of remote file:
- 223 MB
- SHA256:
- b6362abd3f8268f60be884c14f53659e2111b2fd42ec6af38e4d9673d78eb2ae
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.