tensorflow训练数据详细操作

准备工具:

python3.6.2 
pycharm-professional-2017.2.7 
cuda_9.0.176_windows 
cudnn-9.0-windows7-x64-v7.1 
tensorflow-gpu v1.9.0
protoc-3.4.0-win32
ssd_mobilenet_v2_coco_2018_03_29.tar
Git-2.22.0-64-bit

 

下载tensorfow models https://github.com/tensorflow/models

在C:\Program Files\Python36\Lib\site-packages路径目录下，创建文件 tensorflow_model.pth

F:\tensorflow\models\research\slim
F:\tensorflow\models\research\object_detection
F:\tensorflow\models\research

下载protoc-3.4.0-win32.zip 编译tensorflow models支持python

https://github.com/protocolbuffers/protobuf/releases/tag/v3.4.0

 

准备数据：

视频数据 >> http://www.robots.ox.ac.uk/ActiveVision/Research/Projects/2009 bbenfold_headpose/Datasets/TownCentreXVID.avi

标注信息 >> http://www.robots.ox.ac.uk/ActiveVision/Research/Projects/2009 bbenfold_headpose/Datasets/TownCentre-groundtruth.top

将视频数据提取图片保存为jpg

import tensorflow as tf
import cv2 as cv
import os

def video2ims(src,train_path="images",test_path="test_images",factor=2):
    os.mkdir(train_path)
    os.mkdir(test_path)
    frame = 0
    cap = cv.VideoCapture(src)
    counts = int(cap.get(cv.CAP_PROP_FRAME_COUNT))
    w = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
    h = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
    print("number of frames : %d"%counts)
    while True:
        ret, im = cap.read()
        if ret is True:
            if frame < 3600:
                path = train_path
            else:
                path = test_path
            im = cv.resize(im,(w//factor,h//factor))
            cv.imwrite(os.path.join(path,str(frame)+".jpg"),im)
            frame += 1
        else:
            break
    cap.release()

if __name__=="__main__":
    video2ims("F:/opencv/python/video/TownCentreXVID.avi")

生成图片的xml描述文件，需要把生成的jpg图片拷贝到JPEGImages文件夹下，执行代码后，将生成的xml文件拷贝到Annotations文件夹下

import os
import pandas as pd

if __name__ == '__main__':

    GT = pd.read_csv('F:/opencv/python/video/TownCentre-groundtruth.top', header=None)
    indent = lambda x, y: ''.join(['  ' for _ in range(y)]) + x

    factor = 2
    train_size = 3600

    os.mkdir('xmls')
    name = 'pedestrian'
    width, height = 1920 // factor, 1080 // factor

    for frame_number in range(train_size):

        Frame = GT.loc[GT[1] == frame_number]
        x1 = list(Frame[8])
        y1 = list(Frame[11])
        x2 = list(Frame[10])
        y2 = list(Frame[9])
        points = [[(round(x1_), round(y1_)), (round(x2_), round(y2_))] for x1_, y1_, x2_, y2_ in zip(x1, y1, x2, y2)]

        with open(os.path.join('xmls', str(frame_number) + '.xml'), 'w') as file:
            file.write('<annotation>\n')
            file.write(indent('<folder>voc2012</folder>\n', 1))
            file.write(indent('<filename>' + str(frame_number) + '.jpg' + '</filename>\n', 1))
            file.write(indent('<path>F:/pedestrian_data/VOC2012/JPEGImages/' + str(frame_number) + '.jpg' + '</path>\n', 1))
            file.write(indent('<size>\n', 1))
            file.write(indent('<width>' + str(width) + '</width>\n', 2))
            file.write(indent('<height>' + str(height) + '</height>\n', 2))
            file.write(indent('<depth>3</depth>\n', 2))
            file.write(indent('</size>\n', 1))

            for point in points:

                top_left = point[0]
                bottom_right = point[1]

                if top_left[0] > bottom_right[0]:
                    xmax, xmin = top_left[0] // factor, bottom_right[0] // factor
                else:
                    xmin, xmax = top_left[0] // factor, bottom_right[0] // factor

                if top_left[1] > bottom_right[1]:
                    ymax, ymin = top_left[1] // factor, bottom_right[1] // factor
                else:
                    ymin, ymax = top_left[1] // factor, bottom_right[1] // factor

                file.write(indent('<object>\n', 1))
                file.write(indent('<name>' + name + '</name>\n', 2))
                file.write(indent('<pose>Unspecified</pose>\n', 2))
                file.write(indent('<truncated>' + str(0) + '</truncated>\n', 2))
                file.write(indent('<difficult>' + str(0) + '</difficult>\n', 2))
                file.write(indent('<bndbox>\n', 2))
                file.write(indent('<xmin>' + str(xmin) + '</xmin>\n', 3))
                file.write(indent('<ymin>' + str(ymin) + '</ymin>\n', 3))
                file.write(indent('<xmax>' + str(xmax) + '</xmax>\n', 3))
                file.write(indent('<ymax>' + str(ymax) + '</ymax>\n', 3))
                file.write(indent('</bndbox>\n', 2))
                file.write(indent('</object>\n', 1))

            file.write('</annotation>\n')

        print('File:', frame_number, end='\r')

在ImageSets文件夹下创建文件夹Main

在Main文件夹下创建文件，开始创建的pedestrian_train.txt和pedestrian_val.txt的文件后，再后续的操作会直接提示错误 不能打开aeroplane_train.txt和aeroplane_val.txt文件

表示第n张图是否存在行人，1表示存在，0表示不存在，val同理

 

训练数据目录

在data目录下创建 label_map.pbtxt，这里只有一个对象，所以只需要写一个

参考pascal_label_map.pbtxt

 

打开cmd，生成 tf record

python object_detection/dataset_tools/create_pascal_tf_record.py --label_map_path=F:/tensorflow/pedestrian_train/data/label_map.pbtxt --data_dir=F:\pedestrian_data --year=VOC2012 --set=train --output_path=F:/tensorflow/pedestrian_train/data/pascal_train.record


python object_detection/dataset_tools/create_pascal_tf_record.py --label_map_path=F:/tensorflow/pedestrian_train/data/label_map.pbtxt --data_dir=F:\pedestrian_data --year=VOC2012 --set=val --output_path=F:/tensorflow/pedestrian_train/data/pascal_val.record