faster rcnn demo.py:在一個視窗顯示所有類别标注

faster rcnn 的demo.py運作時，對于同一個圖像，每個類别顯示一個視窗，看起來不太友善，順便小改一下，讓一幅圖像中檢測到的所有類别物體都在一個視窗下标注，就友善多了。

代碼改動也不複雜，就是把vis_detections函數中for循環前後三行代碼移動到demo函數的for循環前後。

完整代碼如下(順便把标注框的線寬改成了1，以前是3.5太粗了，不好看)：

py-faster-rcnn/tools/demo.py (注意代碼中本人添加的中文注釋)

#!/usr/bin/env python
#coding=utf8
# 因為代碼中我加了中文注釋，是以 上面這行用于指定編碼 ,否則python代碼執行會報錯 
# --------------------------------------------------------
# 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
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

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')}

#增加ax參數
def vis_detections(im, class_name, dets, ax, thresh=):
    """Draw detected bounding boxes."""
    inds = np.where(dets[:, -] >= thresh)[]
    if len(inds) == :
        return
# 删除這三行
#     im = im[:, :, (2, 1, 0)]
#     fig, ax = plt.subplots(figsize=(12, 12))
#     ax.imshow(im, aspect='equal')
    for i in inds:
        bbox = dets[i, :]
        score = dets[i, -]

        ax.add_patch(
            plt.Rectangle((bbox[], bbox[]),
                          bbox[] - bbox[],
                          bbox[] - bbox[], fill=False,
                          edgecolor='red', linewidth=) # 矩形線寬從3.5改為1
            )
        ax.text(bbox[], bbox[] - ,
                '{:s} {:.3f}'.format(class_name, score),
                bbox=dict(facecolor='blue', alpha=),
                fontsize=, color='white')

    ax.set_title(('{} detections with '
                  'p({} | box) >= {:.1f}').format(class_name, class_name,
                                                  thresh),
                  fontsize=)
# 删除這三行
#     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[])

    # Visualize detections for each class
    CONF_THRESH = 
    NMS_THRESH = 
    # 将vis_detections 函數中for 循環之前的3行代碼移動到這裡
    im = im[:, :, (, , )]
    fig,ax = plt.subplots(figsize=(, ))
    ax.imshow(im, aspect='equal')
    for cls_ind, cls in enumerate(CLASSES[:]):
        cls_ind +=  # because we skipped background
        cls_boxes = boxes[:, *cls_ind:*(cls_ind + )]
        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, :]
        #将ax做為參數傳入vis_detections
        vis_detections(im, cls, dets, ax,thresh=CONF_THRESH)
    # 将vis_detections 函數中for 循環之後的3行代碼移動到這裡
    plt.axis('off')
    plt.tight_layout()
    plt.draw()

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=, 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__':
    cfg.TEST.HAS_RPN = True  # Use RPN for proposals

    args = parse_args()

    prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][],
                            'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
    caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
                              NETS[args.demo_net][])

    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 =  * np.ones((, , ), dtype=np.uint8)
    for i in xrange():
        _, _= 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()