run_img.py

import argparse
import logging
import sys
import time

import cv2
import numpy as np
from tf_pose.estimator import TfPoseEstimator
from tf_pose.networks import get_graph_path, model_wh

logger = logging.getLogger('TfPoseEstimatorImg')
logger.setLevel(logging.DEBUG)
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
formatter = logging.Formatter('[%(asctime)s] [%(name)s] [%(levelname)s] %(message)s')
ch.setFormatter(formatter)
logger.addHandler(ch)


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='tf-pose-estimation run')
    parser.add_argument('--image', type=str, default='./images/p1.jpg')
    parser.add_argument('--model', type=str, default='cmu',
                        help='cmu / mobilenet_thin / mobilenet_v2_large / mobilenet_v2_small')
    parser.add_argument('--resize', type=str, default='432x368',
                        help='if provided, resize images before they are processed. '
                             'default=432x368, Recommends : 432x368 or 656x368 or 1312x736 ')
    parser.add_argument('--resize-out-ratio', type=float, default=4.0,
                        help='if provided, resize heatmaps before they are post-processed. default=4.0')

    args = parser.parse_args()

    w, h = model_wh(args.resize)
    e = TfPoseEstimator(get_graph_path(args.model), target_size=(w, h))

    # 读取单张图像进行识别
    image = cv2.imread(args.image)
    if image is None:
        logger.error('Image can not be read, path=%s' % args.image)
        sys.exit(-1)

    t = time.time()
    humans = e.inference(image, resize_to_default=(w > 0 and h > 0), upsample_size=args.resize_out_ratio)
    elapsed = time.time() - t

    logger.info('inference image: %s in %.4f seconds.' % (args.image, elapsed))

    image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)

    cv2.imshow('result', image)
    cv2.waitKey(0)
    cv2.destroyAllWindows()