TensorFlow目标檢測(object_detection）api使用

• https://github.com/tensorflow/models/tree/master/research/object_detection
• 深度學習目标檢測模型全面綜述：Faster R-CNN、R-FCN和SSD
• 一個應用于物體識别的遷移學習工具鍊：來檢測桃子

請根據

models/blob/master/research/object_detection/g3doc/

目錄下的 installation.md 配置好你的環境

環境搭建可參考：基于win10，GPU的Tensorflow Object Detection API部署及USB攝像頭目标檢測

1. 測試opencv調用usb，c++和python兩個版本

在Ubuntu16.04安裝OpenCV3.1并實作USB攝像頭圖像采集

import cv2
cv2.namedWindow('testcamera', cv2.WINDOW_NORMAL)

capture = cv2.VideoCapture(0)
print (capture.isOpened())
num = 0

while 1:
  ret, img = capture.read()
  cv2.imshow('testcamera', img)
  key = cv2.waitKey(1)
  num += 1
  if key==1048603:#<ESC>
    break

capture.release()
cv2.destroyAllWindows()      

#include <opencv2/core/core.hpp>    
#include <opencv2/highgui/highgui.hpp>    
using namespace cv;  
      
int main(int argc, char** argv) {
    cvNamedWindow("視訊");

    CvCapture* capture = cvCreateCameraCapture(-1);
    IplImage* frame;

    while(1) {
        frame = cvQueryFrame(capture);
        if(!frame) break;
        cvShowImage("視訊", frame);

        char c = cvWaitKey(50);
        if(c==27) break;
    }

    cvReleaseCapture(&capture);
    cvDestroyWindow("視訊");
    return 0;
}      

• python:讀取視訊，處理後，實時計算幀數fps

2. GPU的Tensorflow Object Detection API部署及USB攝像頭目标檢測

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import cv2
import time  

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")

from utils import label_map_util
from 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/dsp/ranjiewen/tensorflow_models/models/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)
print (cap.isOpened())
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):
        
        print("-------")
        ret, frame = cap.read()
        start = time.clock()
        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 fps:',1.0/(end - start))
        #print 'frame:',time.time() - start
        cv2.imshow("capture", image_np)
        cv2.waitKey(1)
cap.release()
cv2.destroyAllWindows()       

 - 速度感覺還可以 。。。

C/C++基本文法學習

STL

C++ primer