基本信息
源码名称:自己手写数字识别
源码大小:114.21M
文件格式:.rar
开发语言:Python
更新时间:2021-04-25
友情提示:(无需注册或充值,赞助后即可获取资源下载链接)
嘿,亲!知识可是无价之宝呢,但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下,绝对物超所值哦!如有下载和支付问题,请联系我们QQ(微信同号):813200300
本次赞助数额为: 3 元×
微信扫码支付:3 元
×
请留下您的邮箱,我们将在2小时内将文件发到您的邮箱
源码介绍
识别自己手写的数字
识别自己手写的数字
def data_prepare(): path = r"C:\Users\Administrator\PycharmProjects\Project\data_recog\data\mnist.npz" # 使用真实绝对路径 (train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data(path) train_images = train_images.reshape((train_images.shape[0],img_row,img_col,1)) test_images = test_images.reshape((test_images.shape[0], img_row, img_col, 1)) train_images = train_images.astype('float32') test_images = test_images.astype('float32') train_images /= 255.0 test_images /= 255.0 print(train_images.shape,train_labels.shape,test_images.shape) print(train_labels[0])