Instructions to use SharpAI/sam2-hiera-tiny-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use SharpAI/sam2-hiera-tiny-onnx with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(SharpAI/sam2-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(SharpAI/sam2-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
File size: 499 Bytes
2b467a1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | {
"model_name": "sam2-hiera-tiny",
"checkpoint_id": "facebook/sam2-hiera-tiny",
"checkpoint_path": "/Users/simba/.cache/huggingface/hub/models--facebook--sam2-hiera-tiny/snapshots/7c218beaf0bb87874785f32b582f640134fc1c09/sam2_hiera_tiny.pt",
"version": "2.0",
"size": "38.9M",
"encoder_path": "encoder.onnx",
"encoder_optimized_path": "encoder.with_runtime_opt.ort",
"decoder_path": "decoder.onnx",
"image_size": 1024,
"mask_size": 256,
"conversion_date": "1763352682.598863"
} |