【Tensorflow实战】一步步创建AlexNet模型识别猫和狗

实际项目见：https://github.com/HiAliens/Cat-and-dog

一、概述
一步步从数据处理和读入开始，到模型创建、训练、测试。
二、所含文件

文件注释里有详细的介绍,详细见上面gitghu地址
三、代码

1. preprocessing.py

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
# author:Dr.Shang


import cv2
import os

import os


def resize(src):
    """
    按照src的目录结构创建剪裁成227*227的图片
    :param src: 需要裁剪图片的根目录
    :return:
    """
    succes = 0
    fail = 0
    fail_file = []
    for root, dirs, files in os.walk(src):
        print('开始文件写入……')
        for file in files:
            filepath = os.path.join(root, file)
            filepath_list = filepath.split('\\')
            # print(filepath)
            # print(filepath_list)
            # print(file)
            try:
                image = cv2.imread(filepath)
                dim = (227, 227)
                resized = cv2.resize(image, dim)
                cwd = os.getcwd()
                new_img_dir = os.path.join(cwd, 'resized_images2')
                # new_img_dir_test = os.path.join(new_img_dir, filepath_list[-3]) 直接在这个地址创建文件夹报错
                # print('test:' + new_img_dir_test)
                if not os.path.exists(new_img_dir):
                    os.mkdir(new_img_dir)
                    # print('success')
                new_img_path = new_img_dir + os.sep + filepath_list[-3]
                # print(new_img_path == new_img_dir_test)
                if not os.path.exists(new_img_path):
                    os.mkdir(new_img_path)
                class_name = new_img_path + os.sep + filepath_list[-2]
                if not os.path.exists(class_name):
                    print('{}文件夹不存在，已创建'.format(class_name))
                    os.mkdir(class_name)
                path = os.path.join(class_name, file)
                if not os.path.exists(path):
                    cv2.imwrite(path, resized)
                    succes += 1
                    # print('写入文件{}成功'.format(path))
                    # pass
            except:
                fail += 1
                path += '\\n'
                fail_file.append(path)
                print(filepath + '文件出错')
                if (succes + fail) % 500 == 0:
                    print('已处理{}张文件，成功{}，失败{}，失败文件请查看fail.txt'.format(succes+fail, succes, fail))
            finally:
                f = open('fail.txt', 'w')
                f.write(fail_file)
    print('总共成功写入{}张，失败{}'.format(succes, fail))



if __name__ == '__main__':
    path = r'D:\DataSet\kaggle\catdog'
    resize(path)

2. GetImageLabel.py

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
# author:Dr.Shang
import os
import numpy as np


def get_file(file_dir):
    '''

    根据指定的训练或验证或测试数据集的路径获取图片集,目录结构应为 file——dir下包含cat和dog两个文件夹
    :param file_dir: 训练数据集文件夹
    :param is_tfr:  以何种方法得到image和label
    :return: image和label
    '''
    images = []
    floders = []
    for root, sub_folders, files in os.walk(file_dir):
        for file in files:
            images.append(os.path.join(root, file))
        for floder in sub_folders:
            floders.append(os.path.join(root, floder))

    labels = []
    for one_floder in floders:
        num_img = len(os.listdir(one_floder)) # 统计one_floder下包含多少个文件
        label = one_floder.split('\\')[-1]
        # print(label)
        if label == 'cats':
            labels = np.append(labels, num_img * [0]) # 生成一个2维列表
        else:
            labels = np.append(labels, num_img * [1])
    # print(len(labels))

    # shuffle
    temp = []
    temp = np.array([images, labels])
    # print(temp)
    temp = temp.transpose()
    # print(temp)
    '''
    [['D:\\DataSet\\kaggle\\small_samples\\test\\cats\\cat.1500.jpg'
  'D:\\DataSet\\kaggle\\small_samples\\test\\cats\\cat.1501.