This repository contains the code supporting the Segment Anything base model for use with Autodistill.
SAM HQ is a zero-shot segmentation model capable of producing detailed masks, developed by ETH VIS. SAM HQ can segment an entire image into masks, or use points to segment specific parts of an object. You can use Segment Anything with Autodistill to segment objects. Segment Anything does not assign classes, so you should use SAM HQ model with a tool like Grounding DINO or GPT-4V.
Read the full Autodistill documentation.
Read the SAM HQ Autodistill documentation.
To use SAM HQ with autodistill, you need to install the following dependency:
pip3 install autodistill-sam-hq
from autodistill_sam_hq import HQSAM
base_model = HQSAM(None)
masks = base_model.predict("./image.jpeg")
print(masks)
This project is licensed under an Apache 2.0 license.
We love your input! Please see the core Autodistill contributing guide to get started. Thank you ๐ to all our contributors!