BirdSpotter SAM21 OpenVINO

OpenVINO conversion of Meta's SAM 2.1 Hiera Large image encoder and box-prompted mask predictor, exported at a fixed 512 x 512 input size for BirdSpotter.

Files

  • openvino-512/sam21_image_encoder.xml and .bin: image encoder IR.
  • openvino-512/sam21_mask_predictor.xml and .bin: prompt and mask decoder IR.
  • manifest.json: SHA-256 checksums and sizes for every packaged artifact.

These models use their normal exported precision; they are not INT8 quantized. See the BirdSpotter repository for preprocessing and box-prompted inference code.

Attribution

This conversion is derived from Meta's facebook/sam2.1-hiera-large checkpoint. Use is subject to the upstream model's license and acceptable-use terms.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support