vgg16.py

import sys
import time

import cv2

import ailia
import vgg16_labels

# import original modules
sys.path.append('../../util')
from utils import get_base_parser, update_parser  # noqa: E402
from model_utils import check_and_download_models  # noqa: E402
from image_utils import load_image  # noqa: E402
from classifier_utils import plot_results, print_results  # noqa: E402
import webcamera_utils  # noqa: E402


# ======================
# Parameters
# ======================
WEIGHT_PATH = 'vgg16_pytorch.onnx'
MODEL_PATH = 'vgg16_pytorch.onnx.prototxt'
REMOTE_PATH = 'https://storage.googleapis.com/ailia-models/vgg16/'

IMAGE_PATH = 'pizza.jpg'
IMAGE_HEIGHT = 224
IMAGE_WIDTH = 224

SLEEP_TIME = 0

# TODO
# model_path = "VGG16.prototxt"
# weight_path = "VGG16.caffemodel"
# img_path = './pizza.jpg'


# ======================
# Arguemnt Parser Config
# ======================
parser = get_base_parser('Image classification model: VGG16', IMAGE_PATH, None)
args = update_parser(parser)


# ======================
# Main functions
# ======================
def recognize_from_image():
    # prepare input data
    input_data = load_image(
        args.input,
        (IMAGE_HEIGHT, IMAGE_WIDTH),
        normalize_type='ImageNet',
        gen_input_ailia=True
    )

    # net initialize
    net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)

    # inference
    print('Start inference...')
    if args.benchmark:
        print('BENCHMARK mode')
        for i in range(5):
            start = int(round(time.time() * 1000))
            preds_ailia = net.predict(input_data)
            end = int(round(time.time() * 1000))
            print(f'\tailia processing time {end - start} ms')
    else:
        preds_ailia = net.predict(input_data)

    # postprocessing
    print_results(preds_ailia, vgg16_labels.imagenet_category)
    print('Script finished successfully.')


def recognize_from_video():
    # net initialize
    net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)

    capture = webcamera_utils.get_capture(args.video)

    # create video writer if savepath is specified as video format
    if args.savepath is not None:
        f_h = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
        f_w = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
        save_h, save_w = webcamera_utils.calc_adjust_fsize(
            f_h, f_w, IMAGE_HEIGHT, IMAGE_WIDTH
        )
        writer = webcamera_utils.get_writer(args.savepath, save_h, save_w)
    else:
        writer = None

    while(True):
        ret, frame = capture.read()
        if (cv2.waitKey(1) & 0xFF == ord('q')) or not ret:
            break

        input_image, input_data = webcamera_utils.preprocess_frame(
            frame, IMAGE_HEIGHT, IMAGE_WIDTH, normalize_type='ImageNet'
        )

        # inference
        preds_ailia = net.predict(input_data)

        # postprocessing
        plot_results(input_image, preds_ailia, vgg16_labels.imagenet_category)
        cv2.imshow('frame', input_image)
        time.sleep(SLEEP_TIME)

        # save results
        if writer is not None:
            writer.write(input_image)

    capture.release()
    cv2.destroyAllWindows()
    if writer is not None:
        writer.release()
    print('Script finished successfully.')


def main():
    # model files check and download
    check_and_download_models(WEIGHT_PATH, MODEL_PATH, REMOTE_PATH)

    if args.video is not None:
        # video mode
        recognize_from_video()
    else:
        # image mode
        recognize_from_image()


if __name__ == '__main__':
    main()