【FPN车辆目标检测】深入解读FPN及Windows7+TensorFlow+Faster-RCNN+FPN代码环境配置和运行过程

 # -*- coding: utf-8 -*-

    
 from __future__ import division, print_function, absolute_import
    
 import sys
    
 sys.path.append('../../')
    
 import xml.etree.cElementTree as ET
    
 import numpy as np
    
 import tensorflow as tf
    
 import glob
    
 import cv2
    
 from help_utils.tools import *
    
 from libs.label_name_dict.label_dict import *
    
 import os
    
  
    
 VOC_dir = 'E:/study_materials/ECCV Vision Meets Drones Challenge/datasets/carData/carData/'
    
 txt_dir = 'TrainAnnotations'
    
 img_dir = 'TrainJPGImages'
    
 save_name = 'train'
    
 save_dir = 'E:/study_materials/ECCV Vision Meets Drones Challenge/FPN_Tensorflow-master（modified）/FPN_Tensorflow-master/data/tfrecords/'
    
 img_format = '.jpg'
    
 dataset = 'car'
    
  
    
 #FLAGS = tf.app.FLAGS
    
  
    
  
    
 def _int64_feature(value):
    
     return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
    
  
    
  
    
 def _bytes_feature(value):
    
     return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
    
  
    
  
    
 def convert_pascal_to_tfrecord():
    
     
    
     save_path = save_dir + dataset + '_' + save_name + '.tfrecord'
    
     mkdir(save_dir)
    
     
    
     label_dir = VOC_dir + txt_dir
    
     image_dir = VOC_dir + img_dir   
    
     
    
     writer = tf.python_io.TFRecordWriter(path=save_path)
    
     
    
     for count, fn in enumerate(os.listdir(image_dir)): 
    
     if ((count+1)%2) != 0:
    
         continue
    
     else:
    
         #print(count+1)
    
         image_fp = os.path.join(image_dir, fn)
    
         image_fp = image_fp.replace('\ ', '/')
    
         label_fp = os.path.join(label_dir, fn.replace('.jpg', '.txt'))
    
         # print('label_fp:',label_fp)
    
              
    
         img_name = str.encode(fn)
    
         
    
         if not os.path.exists(label_fp):
    
             print('{} is not exist!'.format(label_fp))
    
             continue
    
         
    
         # img = np.array(Image.open(img_path))
    
         img = cv2.imread(image_fp)
    
         sizeImg = img.shape
    
         img_height = sizeImg[0]
    
         img_width = sizeImg[1]
    
     
    
         boxes = []
    
         with open(label_fp,'r') as f:
    
             for line in f.readlines():
    
                 line = line.strip().split(',')
    
                 # print('line:',line)
    
                 if line[4] != '0':
    
                     # print(line)
    
                     try:
    
                         line = [int(i) for i in line]
    
                     except:
    
                         line.pop()
    
                         line = [round(float(i)) for i in line]
    
                         # print('line',line)
    
                         #xmin, ymin, xmax, ymax, label   
    
                         #原始标注，xmin,ymin,box_width,box_height,score,category,truncation,occlusion
    
                     if line[4] == 1 and line[5] == 4:
    
                         boxes.append([line[0],line[1],line[0]+line[2],line[1]+line[3],1])
    
     
    
         gtbox_label = np.array(boxes, dtype=np.int32)  # [x1, y1. x2, y2, label]
    
         xmin, ymin, xmax, ymax, label = gtbox_label[:, 0], gtbox_label[:, 1], gtbox_label[:, 2], gtbox_label[:, 3], gtbox_label[:, 4]
    
         gtbox_label = np.transpose(np.stack([ymin, xmin, ymax, xmax, label], axis=0))  # [ymin, xmin, ymax, xmax, label]    
    
         
    
         feature = tf.train.Features(feature={
    
             # maybe do not need encode() in linux
    
             'img_name': _bytes_feature(img_name),
    
             'img_height': _int64_feature(img_height),
    
             'img_width': _int64_feature(img_width),
    
             'img': _bytes_feature(img.tostring()),
    
             'gtboxes_and_label': _bytes_feature(gtbox_label.tostring()),
    
             'num_objects': _int64_feature(gtbox_label.shape[0])
    
         })
    
     
    
         example = tf.train.Example(features=feature)
    
     
    
         writer.write(example.SerializeToString())
    
  
    
     view_bar('Conversion progress', count + 1, len(glob.glob(image_dir + '/*.jpg')))
    
  
    
     print('\nConversion is complete!')
    
  
    
 if __name__ == '__main__':
    
     # xml_path = '../data/dataset/VOCdevkit/VOC2007/Annotations/000005.xml'
    
     # read_xml_gtbox_and_label(xml_path)
    
  
    
     convert_pascal_to_tfrecord()