【深度学习：目标检测】 py-faster-rcnn demo.py解析

转载：http://blog.csdn.net/xzzppp/article/details/52073107

 对py-faster-rcnn/tools/demo.py文件的解析：
    运行该文件：先cd进入到py-faster-rcnn根目录，再在命令后窗口输入: ./tools/demo.py --net myvgg   即可运行

 #程序功能：调用caffemodel，画出检测到的人脸并显示

 #用来指定用什么解释器运行脚本，以及解释器所在位置，这样就可以直接执行脚本
 #!/usr/bin/env python

 # --------------------------------------------------------
 # Faster R-CNN
 # Copyright (c) 2015 Microsoft
 # Licensed under The MIT License [see LICENSE for details]
 # Written by Ross Girshick
 # --------------------------------------------------------

 """
 Demo script showing detections in sample images.

 See README.md for installation instructions before running.
 """

 import _init_paths  #导入“_init_paths.py”文件
 from fast_rcnn.config import cfg
 from fast_rcnn.test import im_detect
 from fast_rcnn.nms_wrapper import nms
 from utils.timer import Timer
 import matplotlib.pyplot as plt  #导入用来画图的工具
 import numpy as np  #numpg:矩阵计算模块
 import scipy.io as sio  #scipy.io：对matlab中mat文件进行读取操作
 import caffe, os, sys, cv2
 import argparse  #argparse：是python用于解析命令行参数和选项的标准模块

 #CLASSES = ('__background__',   #背景 + 类
 #           'aeroplane', 'bicycle', 'bird', 'boat',
 #           'bottle', 'bus', 'car', 'cat', 'chair',
 #           'cow', 'diningtable', 'dog', 'horse',
 #           'motorbike', 'person', 'pottedplant',
 #           'sheep', 'sofa', 'train', 'tvmonitor')

 CLASSES = ('__background__','face')  #只有一类：face

 NETS = {'vgg16': ('VGG16',   #网络
                   'VGG16_faster_rcnn_final.caffemodel'),
         'myvgg': ('VGG_CNN_M_1024',
                   'VGG_CNN_M_1024_faster_rcnn_final.caffemodel'),
         'zf': ('ZF',
                   'ZF_faster_rcnn_final.caffemodel'),
         'myzf': ('ZF',
                   'zf_rpn_stage1_iter_80000.caffemodel'),
 }


 def vis_detections(im, class_name, dets, thresh=0.5):
     """Draw detected bounding boxes."""
     inds = np.where(dets[:, -1] >= thresh)[0]  #返回置信度大于阈值的窗口下标
     if len(inds) == 0:
         return

     im = im[:, :, (2, 1, 0)]
     fig, ax = plt.subplots(figsize=(12, 12))
     ax.imshow(im, aspect='equal')
     for i in inds:
         bbox = dets[i, :4]  #人脸坐标位置（Xmin,Ymin,Xmax,Ymax）
         score = dets[i, -1]  #置信度得分

         ax.add_patch(
             plt.Rectangle((bbox[0], bbox[1]),  #bbox[0]:x, bbox[1]:y, bbox[2]:x+w, bbox[3]:y+h
                           bbox[2] - bbox[0],
                           bbox[3] - bbox[1], fill=False,
                           edgecolor='red', linewidth=3.5)
             )
         ax.text(bbox[0], bbox[1] - 2,
                 '{:s} {:.3f}'.format(class_name, score),
                 bbox=dict(facecolor='blue', alpha=0.5),
                 fontsize=14, color='white')

     ax.set_title(('{} detections with '
                   'p({} | box) >= {:.1f}').format(class_name, class_name,
                                                   thresh),
                   fontsize=14)
     plt.axis('off')
     plt.tight_layout()
     plt.draw()

 def demo(net, image_name):
     #检测目标类，在图片中提议窗口
     """Detect object classes in an image using pre-computed object proposals."""

     # Load the demo image，得到图片绝对地址
     im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name) #拼接路径，返回'A/B/C'之类路径
     im = cv2.imread(im_file)  #读取图片

     # Detect all object classes and regress object bounds
     timer = Timer()  #time.time()返回当前时间
     timer.tic()  #返回开始时间，见'time.py'中
     scores, boxes = im_detect(net, im)  #检测，返回得分和人脸区域所在位置
     timer.toc()  #返回平均时间，'time.py'文件中
     print ('Detection took {:.3f}s for '  #输出
            '{:d} object proposals').format(timer.total_time, boxes.shape[0])

     # Visualize detections for each class
     CONF_THRESH = 0.8
     NMS_THRESH = 0.3
     for cls_ind, cls in enumerate(CLASSES[1:]):  #enumerate:用于遍历序列中元素及他们的下标
         cls_ind += 1 # because we skipped background    ，cls_ind:下标，cls:元素
         cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]  #返回当前坐标
         cls_scores = scores[:, cls_ind]  #返回当前得分
         dets = np.hstack((cls_boxes,  #hstack:拷贝，合并参数
                           cls_scores[:, np.newaxis])).astype(np.float32)
         keep = nms(dets, NMS_THRESH)
         dets = dets[keep, :]
         vis_detections(im, cls, dets, thresh=CONF_THRESH)  #画检测框

 def parse_args():
     """Parse input arguments."""
     parser = argparse.ArgumentParser(description='Faster R-CNN demo')
     parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
                         default=0, type=int)
     parser.add_argument('--cpu', dest='cpu_mode',
                         help='Use CPU mode (overrides --gpu)',
                         action='store_true')
     parser.add_argument('--net', dest='demo_net', help='Network to use [vgg16]',
                         choices=NETS.keys(), default='vgg16')

     args = parser.parse_args()

     return args

 if __name__ == '__main__':  #判断是否在直接运行该.py文件
     cfg.TEST.HAS_RPN = True  # Use RPN for proposals

     args = parse_args()  #模式设置

     prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],  #连接路径，设置prototxt文件
                             'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
     caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
                               NETS[args.demo_net][1])

     if not os.path.isfile(caffemodel):
         raise IOError(('{:s} not found.\nDid you run ./data/script/'
                        'fetch_faster_rcnn_models.sh?').format(caffemodel))

     if args.cpu_mode:
         caffe.set_mode_cpu()
     else:
         caffe.set_mode_gpu()
         caffe.set_device(args.gpu_id)
         cfg.GPU_ID = args.gpu_id
     net = caffe.Net(prototxt, caffemodel, caffe.TEST)  #设置网络

     print '\n\nLoaded network {:s}'.format(caffemodel)

     # Warmup on a dummy image
     im = 128 * np.ones((300, 500, 3), dtype=np.uint8)
     for i in xrange(2):  #xrange是一个类，返回的是一个xrange对象
         _, _= im_detect(net, im)
     #用于演示的图片名
     im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
                 '001763.jpg', '004545.jpg', '001.jpg', '002.jpg', '003.jpg',
                 '004.jpg', '005.jpg', '006.jpg', '007.jpg', '008.jpg']
     for im_name in im_names:
         print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
         print 'Demo for data/demo/{}'.format(im_name)
         demo(net, im_name)  #逐个跑demo

     plt.show()