Tensorflow实现人马图片的分类器 [使用ImageDataGenerator 无需人为标注数据]

本文链接：https://blog.csdn.net/STILLxjy/article/details/98846002

实验环境： goolge colab （改为本地使用也非常的简单，只需将测试部分稍作修改即可）

初始环境：
tmp文件下为空
content文件下只有sample_data文件
在这里插入图片描述
步骤
(1)：下载人马数据集的训练集压缩包和验证集压缩包，放在
/tmp/horse-or-human.zip
/tmp/validation-horse-or-human.zip

!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/horse-or-human.zip \
    -O /tmp/horse-or-human.zip

!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/validation-horse-or-human.zip \
    -O /tmp/validation-horse-or-human.zip

在这里插入图片描述
(2)解压压缩包
训练数据放在/tmp/horse-or-human
验证数据放在/tmp/validation-horse-or-human

import os
import zipfile

local_zip = '/tmp/horse-or-human.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/tmp/horse-or-human')
local_zip = '/tmp/validation-horse-or-human.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/tmp/validation-horse-or-human')
zip_ref.close()

在这里插入图片描述
(3) 定义训练数据和验证数据中人马图片的路径

# Directory with our training horse pictures
train_horse_dir = os.path.join('/tmp/horse-or-human/horses')

# Directory with our training human pictures
train_human_dir = os.path.join('/tmp/horse-or-human/humans')

# Directory with our training horse pictures
validation_horse_dir = os.path.join('/tmp/validation-horse-or-human/horses')

# Directory with our training human pictures
validation_human_dir = os.path