create an efficientnet model according to name. Args: model_name (str): Name for efficientnet. weights_path (None or

Get the input image size for a given efficientnet model. Args: model_name (str): Name for efficientnet. Returns:

Chooses static padding if you have specified an image size, and dynamic padding otherwise. Static padding is necessary for ONNX exporting of mo

Sets swish function as memory efficient (for training) or standard (for export). Args: memory_efficient (bool): Whether to use me

Draw bounding boxes and facial landmarks. Arguments: img: an instance of PIL.Image. bounding_boxes: a float numpy array of shape [