py-faster-rcnn/tools/demo.py

2017-03-12

这个demo.py展示用训练好的VGG16在示例图片上的测试效果。

1._init_paths.py文件，确保py-faster-rcnn/lib和py-fast_rcnn/caffe-fast_rcnn/python加入环境变量

import _init_paths 
from fast_rcnn.config import cfg  #这4个文件都是py-fast_rcnn/lib/fast_rcnn/和/utils目录下的文件
from fast_rcnn.test import im_detect
from fast_rcnn.nms_wrapper import nms
from utils.timer import Timer
import matplotlib.pyplot as plt
import numpy as np
import scipy.io as sio #io可读取matplot文件
import caffe, os, sys, cv2
import argparse #用于解析命令行参数和选项的标准模块
CLASSES = ('__background__',
           'aeroplane', 'bicycle', 'bird', 'boat',
           'bottle', 'bus', 'car', 'cat', 'chair',
           'cow', 'diningtable', 'dog', 'horse',
           'motorbike', 'person', 'pottedplant',
           'sheep', 'sofa', 'train', 'tvmonitor') #[]:列表，():元组，内容不可修改，{}：字典
NETS = {'vgg16': ('VGG16',
                  'VGG16_faster_rcnn_final.caffemodel'),
        'zf': ('ZF',
                  'ZF_faster_rcnn_final.caffemodel')}

2.标上置信度大于0.5的框，标上分类名和置信度，标上标题

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0.5的框在dets中的下标  
    if len(inds) == 0: #如果没有框的置信度大于0.5
        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]
        score = dets[i, -1]
        ax.add_patch(
            plt.Rectangle((bbox[0], bbox[1]),
                          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):
    """Detect object classes in an image using pre-computed object proposals."""
    # Load the demo image
    im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
    im = cv2.imread(im_file)
    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes = im_detect(net, im)
    timer.toc()
    print ('Detection took {:.3f}s for '
           '{: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:]):
        cls_ind += 1 # because we skipped background
        cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
        cls_scores = scores[:, cls_ind]
        dets = np.hstack((cls_boxes,
                          cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(dets, NMS_THRESH)
        dets = dets[keep, :]
        vis_detections(im, cls, dets, thresh=CONF_THRESH)

4.解析./tools/demo.py [此处可以填参数] 传递过来的参数。

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

5.对caffe的配置

if __name__ == '__main__':
    cfg.TEST.HAS_RPN = True  # Use RPN for proposals 修改配置文件py-faster-rcnn/lib/fast-rcnn/config.py 的__C.TEST.HAS_RPN = False
    args = parse_args()
    prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
                            'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')  # 这个路径是~/py-faster-rcnn/models/pascal_voc/VGG16/faster_rcnn_alt_opt/faster_rcnn_test.pt
    caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
                              NETS[args.demo_net][1]) #这个路径是:~/py-faster-rcnn/data/faster_rcnn_models/VGG16_faster_rcnn_final.caffemodel 
    if not os.path.isfile(caffemodel):
        raise IOError(('{:s} not found.\nDid you run ./data/script/'
                       'fetch_faster_rcnn_models.sh?').format(caffemodel)) #出现这个错误是因为你没有下载训练好的模型
    if args.cpu_mode:
        caffe.set_mode_cpu() #设置为cpu模式 在caffe-fast-rcnn/matlab/+caffe/set_mode_cpu.m ？
    else:
        caffe.set_mode_gpu()
        caffe.set_device(args.gpu_id)
        cfg.GPU_ID = args.gpu_id
    net = caffe.Net(prototxt, caffemodel, caffe.TEST) # 网络结构，网络参数，测试
    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):
        _, _= im_detect(net, im) # im_detect方法，返回rpn的score和框 <font color =red>这句看不懂</font>
    im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
                '001763.jpg', '004545.jpg']
    for im_name in im_names:
        print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
        print 'Demo for data/demo/{}'.format(im_name)
        demo(net, im_name)
    plt.show()