def get_images_labels_info()

in extra_scripts/datasets/create_voc_data_files.py [0:0]

• 45 lines of code
• 16 McCabe index (conditional complexity)

def get_images_labels_info(split, args):
    assert g_pathmgr.exists(args.data_source_dir), "Data source NOT found. Abort"

    data_files = get_data_files(split, args)
    # we will construct a map for image name to the vector of -1, 0, 1
    # we sort the data_files which gives sorted class names as well
    img_labels_map = {}
    for cls_num, data_path in enumerate(sorted(data_files)):
        # for this class, we have images and each image will have label
        # 1, -1, 0 -> present, not present, ignore respectively as in VOC data.
        with g_pathmgr.open(data_path, "r") as fopen:
            for line in fopen:
                try:
                    img_name, orig_label = line.strip().split()
                    if img_name not in img_labels_map:
                        img_labels_map[img_name] = -(
                            np.ones(len(data_files), dtype=np.int32)
                        )
                    orig_label = int(orig_label)
                    # in VOC data, -1 (not present), set it to 0 as train target
                    if orig_label == -1:
                        orig_label = 0
                    # in VOC data, 0 (ignore), set it to -1 as train target
                    elif orig_label == 0:
                        orig_label = -1
                    img_labels_map[img_name][cls_num] = orig_label
                except Exception:
                    logger.info(
                        "Error processing: {} data_path: {}".format(line, data_path)
                    )

    img_paths, img_labels = [], []
    for item in sorted(img_labels_map.keys()):
        img_paths.append(f"{args.data_source_dir}/JPEGImages/{item}.jpg")
        img_labels.append(img_labels_map[item])

    output_dict = {}
    if args.generate_json:
        cls_names = []
        for item in sorted(data_files):
            name = item.split("/")[-1].split(".")[0].split("_")[0]
            cls_names.append(name)

        img_ids, json_img_labels = [], []
        for item in sorted(img_labels_map.keys()):
            img_ids.append(item)
            json_img_labels.append(img_labels_map[item])

        for img_idx in range(len(img_ids)):
            img_id = img_ids[img_idx]
            out_lbl = {}
            for cls_idx in range(len(cls_names)):
                name = cls_names[cls_idx]
                out_lbl[name] = int(json_img_labels[img_idx][cls_idx])
            output_dict[img_id] = out_lbl
    return img_paths, img_labels, output_dict