1. 程式人生 > >py-faster-rcnn demo.py解析

py-faster-rcnn demo.py解析

#程式功能:呼叫caffemodel,畫出檢測到的人臉並顯示
 
#用來指定用什麼直譯器執行指令碼,以及直譯器所在位置,這樣就可以直接執行指令碼
#!/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  #匯入“_init_paths.py”檔案
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  #匯入用來畫圖的工具
import numpy as np  #numpg:矩陣計算模組
import scipy.io as sio  #scipy.io:對matlab中mat檔案進行讀取操作
import caffe, os, sys, cv2
import argparse  #argparse:是python用於解析命令列引數和選項的標準模組
 
#CLASSES = ('__background__',   #背景 + 類
#           'aeroplane', 'bicycle', 'bird', 'boat',
#           'bottle', 'bus', 'car', 'cat', 'chair',
#           'cow', 'diningtable', 'dog', 'horse',
#           'motorbike', 'person', 'pottedplant',
#           'sheep', 'sofa', 'train', 'tvmonitor')
 
CLASSES = ('__background__','face')  #只有一類:face
 
NETS = {'vgg16': ('VGG16',   #網路
                  '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]  #返回置信度大於閾值的視窗下標
    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]  #人臉座標位置(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):
	#檢測目標類,在圖片中提議視窗
    """Detect object classes in an image using pre-computed object proposals."""
 
    # Load the demo image,得到圖片絕對地址
    im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name) #拼接路徑,返回'A/B/C'之類路徑
    im = cv2.imread(im_file)  #讀取圖片
 
    # Detect all object classes and regress object bounds
    timer = Timer()  #time.time()返回當前時間
    timer.tic()  #返回開始時間,見'time.py'中
    scores, boxes = im_detect(net, im)  #檢測,返回得分和人臉區域所在位置
    timer.toc()  #返回平均時間,'time.py'檔案中
    print ('Detection took {:.3f}s for '  #輸出
           '{: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:用於遍歷序列中元素及他們的下標
        cls_ind += 1 # because we skipped background    ,cls_ind:下標,cls:元素
        cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]  #返回當前座標
        cls_scores = scores[:, cls_ind]  #返回當前得分
        dets = np.hstack((cls_boxes,  #hstack:拷貝,合併引數
                          cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(dets, NMS_THRESH)
        dets = dets[keep, :]
        vis_detections(im, cls, dets, thresh=CONF_THRESH)  #畫檢測框
 
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__':  #判斷是否在直接執行該.py檔案
    cfg.TEST.HAS_RPN = True  # Use RPN for proposals
 
    args = parse_args()  #模式設定
 
    prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],  #連線路徑,設定prototxt檔案
                            '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)  #設定網路
 
    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是一個類,返回的是一個xrange物件
        _, _= im_detect(net, im)
	#用於演示的圖片名
    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)  #逐個跑demo
 
    plt.show()