為了分析faster-Rcnn的測試結果，需要先將測試結果儲存起來，效果如下：

（圖片名 類別 bbox座標）

程式碼如下：

#!/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
#import matplotlib
#matplotlib.use('Agg')
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
import numpy as np
import scipy.io as sio
import caffe, os, sys, cv2
import argparse
 
 
#自己的類別名稱
CLASSES = ('__background__',
           'one cell missing', 'half cell missing','two cells missing','four cell missing')
 
NETS = {'vgg16': ('VGG16',
                  'VGG16_faster_rcnn_final.caffemodel'),
        'zf': ('ZF',
                  'ZF_faster_rcnn_final.caffemodel')}
 
 
def vis_detections(image_name, class_name, dets, thresh=0.5):
    """Draw detected bounding boxes."""
    inds = np.where(dets[:, -1] >= thresh)[0]
    if len(inds) == 0:
        return
 
    for i in inds:
        bbox = dets[i, :4]
        score = dets[i, -1]
    if(class_name == '__background__'):
        fw = open('./result.txt','a')   #儲存結果的檔案，下同
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu5'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu10'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu15'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu20'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu30'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu40'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu50'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu60'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu70'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu80'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu90'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu100'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu110'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
    elif(class_name == 'xiansu120'):
        fw = open('./result.txt','a')
        fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
        fw.close()
 
 
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, 'VOCdevkit2007','VOC2007','JPEGImages', image_name) #儲存圖片的路徑
    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 = 0.9
    NMS_THRESH = 0.05
    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(image_name, cls, dets, thresh=CONF_THRESH)
 
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='zf')
 
    args = parser.parse_args()
 
    return args
 
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)
    fr = open('./data/demo/test/test1.txt','r') #儲存所有測試圖片名稱的檔案，一行一個檔名
    for im_name in fr:
        im_name = im_name.strip('\n')
        print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
        print 'Demo for test/{}'.format(im_name)
        demo(net,im_name)
        
    plt.show()
    fr.close()