环境
首先安装一下matplotlib库：
sudo pip install matplotlib下载1.4.1的tensorflow
https://github.com/lhelontra/tensorflow-on-arm/releases安装
sudo pip uninstall tensorflow
sudo pip install --upgrade tensorflow-1.4.1-cp27-none-linux_armv7l.whl
准备模型
- 下载tensorflow提供的models API并解压，我这里解压后的目录为
models_master，下载路径：
https://github.com/tensorflow/models/tree/master/research/object_detection/models - 下载训练好的模型并放到上一步
models_master下的object_detection/models目录，下载路径：
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md
这里下载几个典型的：ssd_mobilenet_v1_coco_2017_11_17、faster_rcnn_resnet101_coco和mask_rcnn_inception_v2_coco
注：做物体检测的网络有很多种，如faster rcnn，ssd，yolo等等，通过不同维度的对比，各个网络都有各自的优势。
毕竟树莓派计算能力有限，我们这里先选择专门为速度优化过最快的网络SSD，以及经典的faster-rcnn作对比，再加上能显示mask的高端网络，，，
事实上yolo v3刚出来，比SSD更快，而faster rcnn相对来说运行慢的多了，后面可以都尝试对比一下，目前先把基线系统搭建好。
Protobuf 安装与配置
- 说明
protobuf是Google开发的一种混合语言数据标准，提供了一种轻便高效的结构化数据存储格式，可以用于结构化数据序列化。很适合做数据存储或 RPC 数据交换格式。可用于通讯协议、数据存储等领域的语言无关、平台无关、可扩展的序列化结构数据格式。目前提供了 C++、Java、Python 三种语言的 API。
下载地址：https://github.com/google/protobuf/releases
我们这里下载最新版本protobuf-all-3.5.1.tar.gz - 安装
tar -xf protobuf-all-3.5.1.tar.gz
cd protobuf-3.5.1
./configure
make
make check ->这一步是检查编译是否正确，耗时非常长，可略过
sudo make install
sudo ldconfig ->更新库搜索路径，否则可能找不到库文件
如果运行了make check，结果如下，可以看到所有的测试用例都PASS了，说明编译正确：
============================================================================
Testsuite summary for Protocol Buffers 3.5.1
============================================================================
# TOTAL: 7
# PASS: 7
# SKIP: 0
# XFAIL: 0
# FAIL: 0
# XPASS: 0
# ERROR: 0
============================================================================
- 配置
配置的目的是将proto格式的数据转换为python格式，从而可以在python脚本中调用，进入目录models-master/research，运行：
protoc object_detection/protos/*.proto --python_out=.
转换完毕后可以看到在object_detection/protos/目录下多了许多*.py文件。
代码
这里的代码很简单，因为基本实现都已经有了，我们只是调用一下接口实现功能即可。
import numpy as np
import os
import sys
import tarfile
import tensorflow as tf
import cv2
import time
from collections import defaultdict
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("../..")
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'
#MODEL_NAME = 'faster_rcnn_resnet101_coco_11_06_2017'
#MODEL_NAME = 'ssd_inception_v2_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('/home/yinan/object_detect/models-master/research/object_detection/data', 'mscoco_label_map.pbtxt')
#extract the ssd_mobilenet
start = time.clock()
NUM_CLASSES = 90
#opener = urllib.request.URLopener()
#opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
file_name = os.path.basename(file.name)
if 'frozen_inference_graph.pb' in file_name:
tar_file.extract(file, os.getcwd())
end= time.clock()
print('load the model',(end-start))
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
cap = cv2.VideoCapture(0)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
writer = tf.summary.FileWriter("logs/", sess.graph)
sess.run(tf.global_variables_initializer())
while(1):
start = time.clock()
ret, frame = cap.read()
if cv2.waitKey(1) & 0xFF == ord('q'):
break
image_np=frame
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
scores = detection_graph.get_tensor_by_name('detection_scores:0')
classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Actual detection.
(boxes, scores, classes, num_detections) = sess.run(
[boxes, scores, classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=6)
end = time.clock()
#print('frame:',1.0/(end - start))
print 'One frame detect take time:',end - start
cv2.imshow("capture", image_np)
print('after cv2 show')
cv2.waitKey(1)
cap.release()
cv2.destroyAllWindows()
保存为 detect.py，到目录models-master/research/object_detection/models下。
运行
命令：
sudo chmod 666 /dev/video0
python detect.py
效果
SSD模型
下图可以看到，SSD模型加载模型花了8s，差不多一张图识别时间在5s：
image.png
PS. 为什么把房间识别成了book...
faster-RCNN模型
faster-RCNN，加载模型83s，内存不够，跑不起来。。。
image.png
mask SSD模型
mask模型可以描绘出轮廓，看起来更高端，加载模型25s，遇到个问题：
image.png
接下来查一下
CPU占用率100%，内存占用60%多
