Instructions to use gumka/sam2.1-small-coreml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use gumka/sam2.1-small-coreml with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("gumka/sam2.1-small-coreml") 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("gumka/sam2.1-small-coreml") 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 SAM2_1SmallImageEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/weights/weight.bin from gumka/sam2.1-small-coreml: direct link, hf CLI and curl.
- Browser
- Download file 81.3 MB
-
https://huggingface.co/gumka/sam2.1-small-coreml/resolve/main/SAM2_1SmallImageEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/weights/weight.bin
- Command line
-
hf download hf://gumka/sam2.1-small-coreml/SAM2_1SmallImageEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/weights/weight.bin
-
curl -L -o weight.bin https://huggingface.co/gumka/sam2.1-small-coreml/resolve/main/SAM2_1SmallImageEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/weights/weight.bin
81.3 MB
- Xet hash:
- 92e77fd66a0de1844a118e95fb90055b42731b1af48e5e647461dcfad6646ab2
- Size of remote file:
- 81.3 MB
- SHA256:
- 6128a58f10cbcb7797bd12a7ec1e05ab4e9f8c80bd14ed05bbc43a9c9935a9c3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.