Computer Vision News - August 2021

3 Summary 1 InnerEye by Microsoft Building up models The next step would be to start building model. Of course, if there’s a pre-existing model, it can be ported to the InnerEye system; let’s see how! A configuration settings.yml, a folder whic h includes model configurations (InnerEyeLocal) and a file InnerEyeLocal/ML /runner.py are needed. Below such a sample file is shown: from pathlib import Path import os from InnerEye.ML import runner def main() -> None: current = os.path.dirname(os.path.realpath(__file__)) project_root = Path(os.path.realpath(os.path.join(current, "..", ".."))) runner.run(project_root=project_root, yaml_config_file=project_root / "relative/path/to/settings.yml", post_cross_validation_hook=None) if __name__ == '__main__': main() Let’s say a prostate segmentation is run. The model can be simply inherited from a base ProstateBase parent file and an example would be as follows: from InnerEye.ML.configs.segmentation.ProstateBase import ProstateBase class Prostate(ProstateBase): def __init__(self) -> None: super().__init__( ground_truth_ids=["femur_r", "femur_l", "rectum", "prostate"], azure_dataset_id="name-of-your-AML-dataset-with-prostate-data") Similarly, for a head and neck model, the inheritance and sample code are shown below: from InnerEye.ML.configs.segmentation.HeadAndNeckBase import HeadAndNeckBase