def convert_mask_in_VOC_to_jsonl()

in cli/foundation-models/system/finetune/image-instance-segmentation/jsonl_converter.py [0:0]

• 62 lines of code
• 8 McCabe index (conditional complexity)

def convert_mask_in_VOC_to_jsonl(dataset_dir: str, remote_path: str) -> None:
    """
    :param dataset_dir: Path to dataset directory, where user has images and anotations
    :type: dataset_dir: String
    :param remote_path: Remote path for dataset
    :type: remote_path: String
    """

    dataset_parent_dir = os.path.dirname(dataset_dir)
    print(dataset_dir, dataset_parent_dir)

    # We will copy each JSONL file within its related MLTable folder
    training_mltable_path = os.path.join(dataset_parent_dir, "training-mltable-folder")
    validation_mltable_path = os.path.join(
        dataset_parent_dir, "validation-mltable-folder"
    )

    # Create the folders if they don't exist
    os.makedirs(training_mltable_path, exist_ok=True)
    os.makedirs(validation_mltable_path, exist_ok=True)

    train_validation_ratio = 5

    # Path to the training and validation files
    train_annotations_file = os.path.join(
        training_mltable_path, "train_annotations.jsonl"
    )
    validation_annotations_file = os.path.join(
        validation_mltable_path, "validation_annotations.jsonl"
    )

    # Path to the annotations
    annotations_folder = os.path.join(dataset_dir, "annotations")
    mask_folder = os.path.join(dataset_dir, "segmentation-masks")

    # Sample json line dictionary
    json_line_sample = {
        "image_url": remote_path,
        "image_details": {"format": None, "width": None, "height": None},
        "label": [],
    }

    # Read each annotation and convert it to jsonl line
    with open(train_annotations_file, "w") as train_f:
        with open(validation_annotations_file, "w") as validation_f:
            for i, filename in enumerate(os.listdir(annotations_folder)):
                if not filename.endswith(".xml"):
                    print(f"Skipping unknown file: {filename}")
                    continue

                annotation_file_path = os.path.join(annotations_folder, filename)
                print(f"Parsing {annotation_file_path}")

                root = ET.parse(annotation_file_path).getroot()
                width = int(root.find("size/width").text)
                height = int(root.find("size/height").text)

                # Convert mask into polygon
                mask_fname = os.path.join(mask_folder, filename[:-4] + ".png")
                polygons = parsing_mask(mask_fname)

                labels = []
                for index, object in enumerate(root.findall("object")):
                    name = object.find("name").text
                    isCrowd = int(object.find("difficult").text)
                    labels.append(
                        {
                            "label": name,
                            "bbox": "null",
                            "isCrowd": isCrowd,
                            "polygon": polygons[index],
                        }
                    )

                # Build the jsonl file
                image_filename = root.find("filename").text
                _, file_extension = os.path.splitext(image_filename)
                json_line = dict(json_line_sample)
                json_line["image_url"] = (
                    json_line["image_url"] + "images/" + image_filename
                )
                json_line["image_details"]["format"] = file_extension[1:]
                json_line["image_details"]["width"] = width
                json_line["image_details"]["height"] = height
                json_line["label"] = labels

                if i % train_validation_ratio == 0:
                    # Validation annotation
                    validation_f.write(json.dumps(json_line) + "\n")
                else:
                    # Train annotation
                    train_f.write(json.dumps(json_line) + "\n")