无法在keras中加载mnist数据集 [英] cant load mnist dataset in keras

查看:615
本文介绍了无法在keras中加载mnist数据集的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

im尝试通过以下方式加载mnist数据集:

im trying to load the mnist dataset by :

import keras
from keras.datasets import mnist
(x_train,y_train),(x_test,y_test)=mnist.load_data()

但是我得到这个错误:

  Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "E:\anaconda\lib\site-packages\keras\datasets\mnist.py", line 15, in load_data
  data = cPickle.load(f)
  File "E:\anaconda\lib\gzip.py", line 252, in read
  raise IOError(errno.EBADF, "read() on write-only GzipFile object")
  IOError: [Errno 9] read() on write-only GzipFile object

我该怎么办?

谢谢

推荐答案

MNIST手写数字数据库

包含10位数的60,000张28x28灰度图像的数据集,以及10,000张图像的测试集.

Dataset of 60,000 28x28 grayscale images of the 10 digits, along with a test set of 10,000 images.

用法:

  from keras.datasets import mnist

  (x_train, y_train), (x_test, y_test) = mnist.load_data()

返回:

2个元组: x_train,x_test:uint8形状为(num_samples,28,28)的灰度图像数据数组.

2 tuples: x_train, x_test: uint8 array of grayscale image data with shape (num_samples, 28, 28).

y_train,y_test:uint8形状为(num_samples)的数字标签数组(范围为0-9的整数). 参数:

y_train, y_test: uint8 array of digit labels (integers in range 0-9) with shape (num_samples,). Arguments:

注意(路径:如果本地没有索引文件(位于'〜/.keras/datasets/'+路径),则它将下载到该位置.)

Note(path: if you do not have the index file locally (at '~/.keras/datasets/' + path), it will be downloaded to this location.)

这篇关于无法在keras中加载mnist数据集的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆