Instructions to use cstr/sam2.1-hiera-tiny-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use cstr/sam2.1-hiera-tiny-ONNX with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("cstr/sam2.1-hiera-tiny-ONNX") 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("cstr/sam2.1-hiera-tiny-ONNX") 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 decoder.onnx from cstr/sam2.1-hiera-tiny-ONNX: direct link, hf CLI and curl.
- Browser
- Download file 20.7 MB
-
https://huggingface.co/cstr/sam2.1-hiera-tiny-ONNX/resolve/main/decoder.onnx
- Command line
-
hf download hf://cstr/sam2.1-hiera-tiny-ONNX/decoder.onnx
-
curl -L -o decoder.onnx https://huggingface.co/cstr/sam2.1-hiera-tiny-ONNX/resolve/main/decoder.onnx
20.7 MB
- Xet hash:
- a2d0717d36212a350059425debb9c0a313134fb9873e672edf875d5dccfbe74d
- Size of remote file:
- 20.7 MB
- SHA256:
- 0ae944e08e55814c19afa4d143ef07b1a3dbad2decd77c15ec3ab220b9f57247
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.