Faster—RCNN源代码解析之demo.py

1、模型选择，以及分类类型：

CLASSES = ('__background__', 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor') NETS = {'vgg16': ('VGG16', 'VGG16_faster_rcnn_final.caffemodel'), 'zf': ('ZF', 'ZF_faster_rcnn_final.caffemodel')}

CLASSES后面的是你需要分类目标的名称，NETS后面的是你训练好的模型的名称。

2、vis_detections函数，用来使得检测结果可视化，即在图片中展示出检测结果，包括物体框和类别以及得分。

def vis_detections(im, class_name, dets, thresh=0.5): """Draw detected bounding boxes.""" inds = np.where(dets[:, -1] >= thresh)[0] 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] 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()

3，demo()函数： 使用训练好的模型对测试样本进行物体探测测试：

def demo(net, image_name): """Detect object classes in an image using pre-computed object proposals.""" # Load the demo image #使用你自己的路径时做相应的修改即可 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、parse_args（）函数： 没有太大的修改

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、主函数： 使用主函数，调用预定义函数得出最终结果：

if __name__ == '__main__': cfg.TEST.HAS_RPN = True # Use RPN for proposals args = parse_args() prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0], '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) 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_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()