基于卷积神经网络的猫狗识别

任务要求：

1.按照 https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/5.2-using-convnets-with-small-datasets.ipynb,
2.利用TensorFlow和Keras，自己搭建卷积神经网络完成狗猫数据集的分类实验；将关键步骤用汉语注释出来。解释什么是overfit（过拟合）?什么是数据增强？如果单独只做数据增强，精确率提高了多少？然后再添加的dropout层，是什么实际效果？
3.用Vgg19网络模型完成狗猫分类，写出实验结果；
4.（选做）不用TensorFlow，改用pytorch，进行狗猫分类实验。

实验环境：jupter-notebook

一、环境配置

1.anaconda的安装

这里提供两个anaconda的下载链接

清华下载源：https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/
官方安装教程：http://docs.anaconda.com/anaconda/install/windows/

结果展示：

2.jupyter notebook配置

• 1.添加jupyter_contrib_nbextensions插件
  （1）安装jupyter_contrib_nbextensions库：

pip install jupyter_contrib_nbextensions -i https://pypi.douban.com/simple/

（2）配置到jupyter

jupyter contrib nbextension install --user --skip-running-check

（3）重启jupyter notebook

勾选选项： “Table of Contents” 以及 “Hinterland”等

3.安装TensorFlow、Keras包

命令行安装：

pip install tensorflow
pip install keras

二、入门实例：猫狗识别

1.猫狗数据集的准备

先从kaggle网站的数据集下载下来猫狗数据集

解压之后如图所示：

在训练集（train）中有很多关于猫狗的图片

2.进行猫狗识别

图片分类并打印出结果：

import os, shutil
# The path to the directory where the original
# dataset was uncompressed（原始数据集路径）
original_dataset_dir = 'C:/Users/23226/Desktop/kaggle_Dog&Cat/train/train'

# The directory where we will
# store our smaller dataset（目标存储路径）
base_dir = 'C:/Users/23226/Desktop/kaggle_Dog&Cat/result'
os.mkdir(base_dir)

# Directories for our training,
# validation and test splits
train_dir = os.path.join(base_dir, 'train')
os.mkdir(train_dir)
validation_dir = os.path.join(base_dir, 'validation')
os.mkdir(validation_dir)
test_dir = os.path.join(base_dir, 'test')
os.mkdir(test_dir)

# Directory with our training cat pictures
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)

# Directory with our training dog pictures
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)

# Directory with our validation cat pictures
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)

# Directory with our validation dog pictures
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)

# Directory with our validation cat pictures
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)

# Directory with our validation dog pictures
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)

# Copy first 1000 cat images to train_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(train_cats_dir, fname)
    shutil.copyfile(src, dst)

# Copy next 500 cat images to validation_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(validation_cats_dir, fname)
    shutil.copyfile(src