ConnectionResetError: [Errno 104] Connection reset by peer

fetch_mldata函数无法下载MNIST数据集问题

from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original')

解决方案

1. 下载数据集

!wget https://github.com/amplab/datascience-sp14/raw/master/lab7/mldata/mnist-original.mat

2. 查看sklearn数据根目录

from sklearn.datasets.base import get_data_home 
print (get_data_home())

!tree /root/scikit_learn_data

3. 复制数据集至mldata目录

!cp mnist-original.mat /root/scikit_learn_data/mldata
!tree /root/scikit_learn_data

4. 验证

from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original')

mnist

5. OK！！！

mnist.data.shape

mnist.target.shape

补充

from sklearn.datasets import fetch_openml	
mnist = fetch_openml('mnist_784', version=1)

下载不下来啊啊啊！

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./data/")