基于卷积神经网络的猫狗识别

一、配置环境

这里我用命令行创建虚拟环境

• 输入如下命令创建虚拟环境

conda create -n cat_dog python=3.8 #cat_dog为环境名，python版本为3.8

• 如图，输入y
  

• 如图，说明安装成功
  

• 输入命令进入 cat_dog 虚拟环境

activate
conda activate cat_dog

• 进入环境后，下载所需包

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

二、准备数据集

数据集的下载
kaggle网站的数据集下载地址：https://www.kaggle.com/lizhensheng/-2000
或百度网盘下载：https://pan.baidu.com/s/13hw4LK8ihR6-6-8mpjLKDA
提取码：dmp4

1.将下载的数据集解压

2.进入jupyter notebook，输入如下代码对图片进行分类

import tensorflow as tf
import keras
import os, shutil 
# 原始目录所在的路径
original_dataset_dir = 'G:\\Cat_And_Dog\\kaggle\\train\\'

# 数据集分类后的目录
base_dir = 'G:\\Cat_And_Dog\\kaggle\\cats_and_dogs_small'
os.mkdir(base_dir)

# # 训练、验证、测试数据集的目录
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)

# 猫训练图片所在目录
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)

# 狗训练图片所在目录
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)

# 猫验证图片所在目录
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)

# 狗验证数据集所在目录
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)

# 猫测试数据集所在目录
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)

# 狗测试数据集所在目录
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)

# 将前1000张猫图像复制到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)

# 将下500张猫图像复制到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, dst)
    
# 将下500张猫图像复制到test_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(test_cats_dir, fname)
    shutil.copyfile(src, dst)
    
# 将前1000张狗图像复制到train_dogs_dir
fnames = ['dog.{}.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_dogs_dir, fname)
    shutil.copyfile(src, dst)
    
# 将下500张狗图像复制到validation_dogs_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path