Mask Generation
sam2
segment-anything
instance-segmentation
robotics
IB-Robot
ascend
edge-deployment
Instructions to use openEuler/sam2.1_hiera_tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use openEuler/sam2.1_hiera_tiny with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("openEuler/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("openEuler/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 assets/adapter.json from openEuler/sam2.1_hiera_tiny: direct link, hf CLI and curl.
- Browser
- Download file 453 Bytes
-
https://huggingface.co/openEuler/sam2.1_hiera_tiny/resolve/main/assets/adapter.json
- Command line
-
hf download hf://openEuler/sam2.1_hiera_tiny/assets/adapter.json
-
curl -L -o adapter.json https://huggingface.co/openEuler/sam2.1_hiera_tiny/resolve/main/assets/adapter.json
453 Bytes
| { | |
| "checkpoint": "assets/sam2.1_hiera_tiny.pt", | |
| "config": "configs/sam2.1/sam2.1_hiera_t.yaml", | |
| "interface": "tensor_model", | |
| "model_type": "sam2", | |
| "operation": "automatic", | |
| "points_per_batch": 16, | |
| "points_per_side": 64, | |
| "postprocessing": "automatic-masks-v1", | |
| "pred_iou_thresh": 0.72, | |
| "preprocessing": "sam2-rgb-uint8-v1", | |
| "stability_score_thresh": 0.9, | |
| "torch_module_loader": "perception_service.torch_model_loaders:load_sam2" | |
| } | |