Instructions to use inference4j/sam2.1-hiera-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use inference4j/sam2.1-hiera-tiny with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("inference4j/sam2.1-hiera-tiny") 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("inference4j/sam2.1-hiera-tiny") 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.onnx_data from inference4j/sam2.1-hiera-tiny: direct link, hf CLI and curl.
- Browser
- Download file 134 MB
-
https://huggingface.co/inference4j/sam2.1-hiera-tiny/resolve/main/vision_encoder.onnx_data
- Command line
-
hf download hf://inference4j/sam2.1-hiera-tiny/vision_encoder.onnx_data
-
curl -L -o vision_encoder.onnx_data https://huggingface.co/inference4j/sam2.1-hiera-tiny/resolve/main/vision_encoder.onnx_data
134 MB
- Xet hash:
- b3f0afad0ec0be90b7279bd1416269c019f4e9a3b44e128261fff4fe77e80139
- Size of remote file:
- 134 MB
- SHA256:
- e83df9866a5afe68ea7f0f721f18f65137fc3acbf0da1c74e946d363e09c69cc
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.