SSD: Single Shot MultiBox Detector检测单张图片

准备工作

当然，首先你要把SSD按照教程编译好，设置好python环境变量，然后重启计算机（建议），开始本次工作。SSD项目检测单张图片有C++程序和ipython程序，这里建议用ipython，主要是方便简单。该工具路径为/home/mx/caffe/example/ssd_detect.ipynb，使用jupyter notebook工具操作。

下载SSD模型

该工具使用的模型是VGG_VOC0712_SSD_300x300_iter_60000.caffemodel，为了第一次就成功，我们就用它了，下载完后解压，把里面的VGGNet文件夹移动到/home/mx/caffe/models/之下。当然，你掌握这个程序后，完全可以修改路径，检测其他模型的效果。

运行程序检测单张图片,在vim中打开的网页中按照路径找到ssd_detect.ipynb，打开后发现是上面这样。

复制到的代码，并且改写代码如下：

#coding=utf-8
#
#First, Load necessary libs and set up caffe and caffe_root、
#
import cv2
import numpy as np
import matplotlib.pyplot as plt


plt.rcParams['figure.figsize'] = (10, 10)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

# Make sure that caffe is on the python path:
caffe_root = '/home/shawn/caffe/'  # this file is expected to be in {caffe_root}/examples
import os
os.chdir(caffe_root)
import sys
sys.path.insert(0, 'python')

import caffe
caffe.set_device(0)
caffe.set_mode_gpu()

#
#Load LabelMap.
#Load the net in the test phase for inference, and configure input preprocessing.
#
model_def = '/home/shawn/caffe/models/VGGNet/VOC0712/SSD_300x300/deploy.prototxt'
model_weights = '/home/shawn/caffe/models/VGGNet/VOC0712/SSD_300x300/VGG_VOC0712_SSD_300x300_iter_60000.caffemodel'

net = caffe.Net(model_def,      # defines the structure of the model
                model_weights,  # contains the trained weights
                caffe.TEST)     # use test mode (e.g., don't perform dropout)

# input preprocessing: 'data' is the name of the input blob == net.inputs[0]
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2, 0, 1))
transformer.set_mean('data', np.array([104,117,123])) # mean pixel
transformer.set_raw_scale('data', 255)  # the reference model operates on images in [0,255] range instead of [0,1]
transformer.set_channel_swap('data', (2,1,0))  # the reference model has channels in BGR order instead of RGB

#——————————————————————————————————————————————————————————————————————————————
from google.protobuf import text_format
from caffe.proto import caffe_pb2

# load PASCAL VOC labels
labelmap_file = '/home/shawn/caffe/data/VOC0712/labelmap_voc.prototxt'
file = open(labelmap_file, 'r')
labelmap = caffe_pb2.LabelMap()
text_format.Merge(str(file.read()), labelmap)

def get_labelname(labelmap, labels):
    num_labels = len(labelmap.item)
    labelnames = []
    if type(labels) is not list:
        labels = [labels]
    for label in labels:
        found = False
        for i in xrange(0, num_labels):
            if label == labelmap.item[i].label:
                found = True
                labelnames.append(labelmap.item[i].display_name)
                break
        assert found == True
    return labelnames


#
#Load an image.
#

# set net to batch size of 1
image_resize = 300
net.blobs['data'].reshape(1,3,image_resize,image_resize)

image = caffe.io.load_image('/data/video/meizi9.jpg')
plt.imshow(image)


#
#Run the net and examine the top_k results
#
transformed_image = transformer.preprocess('data', image)
net.blobs['data'].data[...] = transformed_image

# Forward pass.
detections = net.forward()['detection_out']

# Parse the outputs.
det_label = detections[0,0,:,1]
det_conf = detections[0,0,:,2]
det_xmin = detections[0,0,:,3]
det_ymin = detections[0,0,:,4]
det_xmax = detections[0,0,:,5]
det_ymax = detections[0,0,:,6]

# Get detections with confidence higher than 0.6.
top_indices = [i for i, conf in enumerate(det_conf) if conf >= 0.6]

top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_labels = get_labelname(labelmap, top_label_indices)
top_xmin = det_xmin[top_indices]
top_ymin = det_ymin[top_indices]
top_xmax = det_xmax[top_indices]
top_ymax = det_ymax[top_indices]

#
#Plot the boxes
#
colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()

plt.imshow(image)
currentAxis = plt.gca()


for i in xrange(top_conf.shape[0]):
    xmin = int(round(top_xmin[i] * image.shape[1]))
    ymin = int(round(top_ymin[i] * image.shape[0]))
    xmax = int(round(top_xmax[i] * image.shape[1]))
    ymax = int(round(top_ymax[i] * image.shape[0]))
    score = top_conf[i]
    label = int(top_label_indices[i])
    label_name = top_labels[i]
    display_txt = '%s: %.2f'%(label_name, score)
    coords = (xmin, ymin), xmax-xmin+1, ymax-ymin+1
    color = colors[label]
    currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor=color, linewidth=2))
    currentAxis.text(xmin, ymin, display_txt, bbox={'facecolor':color, 'alpha':0.5})

plt.show()
"""
while True:  
    cv2.imshow('frame',image)#一个窗口用以显示原视频  
    if cv2.waitKey(1) &0xFF == ord('q'):  
        break  
"""