How to use onnx model to inference a image and get all mask?

I want to all object mask from image in using onnx model, but the example for onnx inference is not my expectation.Who knows how to use the onnx model to reason the way to get all the objects in the image, please feel free to teach me, thank you!!

Start with the repository's existing ONNX inference example and compare its documented output with the request for masks for every object in one image. The issue names no file, test, or entry point, so first determine where that example is maintained and clarify the expected mask output; done would be a documented, reproducible inference path.

Written by the indexing model from the issue text.