TensorFlow数据集提取图片

以cifar10为例:

import os
import tensorflow as tf
import matplotlib.pyplot as plt

(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.cifar10.load_data()

class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']

index_to_name = {i: name for i, name in enumerate(class_names)}

#根据class_name创建不同的文件夹
for index,name in index_to_name.items():
    
    path = os.path.join('./data/train', name)
    os.makedirs(path, exist_ok=True)

for index,name in index_to_name.items():
    
    path = os.path.join('./data/test', name)
    os.makedirs(path, exist_ok=True)

#读取cifar10数据集,并将其保存到对应的文件夹中
(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.cifar10.load_data()

for i in range(train_images.shape[0]):
    img = train_images[i]
    label = train_labels[i][0]
    name = index_to_name[label]
    
    path = os.path.join('./data/train', name, f'{i}.png')
    plt.imsave(path, img)

for i in range(test_images.shape[0]):
    img = test_images[i]
    label = test_labels[i][0]
    name = index_to_name[label]
    
    path = os.path.join('./data/test', name, f'{i}.png')
    plt.imsave(path, img)

  • 4
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值