基于MobileNetV2-SSD缺陷检测

基于MobileNetV2-SSD缺陷检测

（1） SSD论文连接
（2） MobileNetV2连接

实验部分

一 环境搭配

win10
pycharm
anaconda
cuda + cudnn
python 3.x
tensorflow-gpu
下载代码库
下载protoc作用是将Tensorflow object detection API模型文件中的.pro
文件编译成python文件。直接输入：protoc ./object_detection/protos/*.proto --python_out=. 就可以快速编译所有文件

添加两个环境变量：
\models\research
\models\research\slim
安装research & slim
cd slim
python setup.py install

测试是否安装成功（research目录）
python object_detection/builders/model_builder_test.py
安装成功会显示ok

二制作数据集

下载labelimg-master
打开cmd, 进入labelImg目录：
运行：
pyrcc5 -o resources.py resources.qrc命令
python labelImg.py
就可以打开labelImg了
通过画矩形框，打上标签，生成xml文件新建data文件夹，并生成train，test两个子文件夹

xlm转csv

"""
Created on 2020 7 11

@author: Huang hanlin
"""

import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET

os.chdir('E:\\model-master\\research\\object_detection\\data\\imagess\\test')
path = 'E:\\model-master\\research\\object_detection\\data\\imagess\\test'

def xml_to_csv(path):
    xml_list = []
    for xml_file in glob.glob(path + '/*.xml'):
        tree = ET.parse(xml_file)
        root = tree.getroot()
        for member in root.findall('object'):
            value = (root.find('filename').text,
                     int(root.find('size')[0].text),
                     int(root.find('size')[1].text),
                     member[0].text,
                     int(member[4][0].text),
                     int(member[4][1].text),
                     int(member[4][2].text),
                     int(member[4][3].text)
                     )
            xml_list.append(value)
    column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
    xml_df = pd.DataFrame(xml_list, columns=column_name)
    return xml_df


def main():
    image_path = path
    xml_df = xml_to_csv(image_path)
    xml_df.to_csv('maosi_test.csv', index=None)
    print('Successfully converted xml to csv.')


main()

csv生成tf文件

from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
#python generate_tfrecord.py --csv_input=maosi_train.csv  --image_dir=train --output_path=train.record
import os
import io
import pandas as pd
import tensorflow as tf

from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict

flags = tf.app.flags
flags.DEFINE_string('csv_input', '', 'Path to the CSV input')
flags.DEFINE_string('image_dir', '', 'Path to the image directory')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
FLAGS = flags.FLAGS


# TO-DO replace this with label map
def class_text_to_int(row_label):
    if row_label == 'stain':
        return 1
    else:
        return None


def split(df, group):
    data = namedtuple('data', ['filename', 'object'])
    gb = df.groupby(group)
    return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]


def create_tf_example(group, path):
    with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
        encoded_jpg = fid.read()
    encoded_jpg_io = io.BytesIO(encoded_jpg)
    image = Image.open(encoded_jpg_io)
    width, height = image.size

    filename = group.filename.encode('utf8')
    image_format = b'jpg'
    xmins = []
    xmaxs = []
    ymins = []
    ymaxs = []
    classes_text = []
    classes = []

    for index, row in group.object.iterrows():
        xmins.append(row['xmin'] / width)
        xmaxs.append(row['xmax'] / width)
        ymins.append(row['ymin'] / height)
        ymaxs.append(row['ymax'] / height)
        classes_text.append(row['class'].encode('utf8'))
        classes.append(class_text_to_int(row['class']))

    tf_example = tf.train.Example(features=tf.train.Features(feature={
        'image/height': dataset_util.int64_feature(height),
        'image/width': dataset_util.int64_feature(width),
        'image/filename': dataset_util.bytes_feature(filename),
        'image/source_id': dataset_util.bytes_feature(filename),
        'image/encoded': dataset_util.bytes_feature(encoded_jpg),
        'image/format': dataset_util.bytes_feature(image_format),
        'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
        'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
        'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
        'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
        'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
        'image/object/class/label': dataset_util.int64_list_feature(classes),
    }))
    return tf_example


def main(_):
    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
    path = os.path.join(os.getcwd(), FLAGS.image_dir)
    examples = pd.read_csv(FLAGS.csv_input)
    grouped = split(examples, 'filename')
    for group in grouped:
        tf_example = create_tf_example(group, path)
        writer.write(tf_example.SerializeToString())

    writer.close()
    output_path = os.path.join(os.getcwd(), FLAGS.output_path)
    print('Successfully created the TFRecords: {}'.format(output_path))


if __name__ == '__main__':
    tf.app.run()

生成.pbtxt文件，内容为缺陷类别

三训练模型

1 下载fine-tune模型
2 修改参数
打开ssd_mobilenet_v2_coco.config，修改类别数目

3 fine-tune模型地址

4 修改数据集传输入口

4 cmd界面下执行python model_main.py --pipeline_config_path=training/ssdlite_mobilenet_v2_coco.config --model_dir=training --alsologtostder命令就可以开始训练了

四实验结果

生成checkpoint文件通过tensorboard --logdir=training查看

五表演真正技术时候到了

六 欢迎加我的github交流

本文地址：https://blog.csdn.net/weixin_42679015/article/details/107288438