src/get_data_coco/get_img.py

from pycocotools.coco import COCO
import requests
import yaml

def get_images(cfg_path = 'cfg/cfg.yml'):
    """To query and get coco dataset by a certain subset e.g. 'person'

    Args:
        path (str, optional): _description_. Defaults to 'data/annotations_trainval2017/annotations/instances_val2017.json'.
        catNms (list, optional): _description_. Defaults to ['person'].
    """

    cfg_file = open(cfg_path)
    cfg = yaml.load(cfg_file, Loader=yaml.FullLoader)

    # instantiate COCO specifying the annotations json path
    coco = COCO(cfg['dataset']['annotations_folder_path'] + cfg['dataset']['annotations_fname'])
    # Specify a list of category names of interest
    catIds = coco.getCatIds(catNms=cfg['dataset']['classes'])
    # Get the corresponding image ids and images using loadImgs
    imgIds = coco.getImgIds(catIds=catIds)
    images = coco.loadImgs(imgIds)

    # Save the images into a local folder
    for im in images:
        img_data = requests.get(im['coco_url']).content
        with open(cfg['dataset']['img_folder_path'] + im['file_name'], 'wb') as handler:
            handler.write(img_data)

    return

if __name__ == '__main__':
    get_images(cfg_path = 'cfg/cfg.yml')