Question

我正在尝试从计算机中将语言环境MNIST数据集导入Jupyter Notebook，但出现ModuleNotFound错误。

我已经安装了python-mnist软件包

# Import necessary modules 
from sklearn.neighbors import KNeighborsClassifier 
from sklearn.model_selection import train_test_split
from mnist import MNIST

import numpy as np 
import matplotlib.pyplot as plt 

mnist = MNIST('../Dataset/MNIST')
x_train, y_train = mnist.load_training() #60000 samples
x_test, y_test = mnist.load_testing()    #10000 samples

THE ERROR MESSAGE
---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
<ipython-input-1-4e881af1c89c> in <module>
      2 from sklearn.neighbors import KNeighborsClassifier
      3 from sklearn.model_selection import train_test_split
----> 4 from mnist import MNIST
      5 
      6 import numpy as np

ModuleNotFoundError: No module named 'mnist'

Answer 1

尝试使用：

import tensorflow_datasets as tfds
datasets = tfds.load('mnist')

train_dataset = datasets['train']
test_dataset = datasets['test']

IMAGE_INPUT_NAME = 'image'
LABEL_INPUT_NAME = 'label'

https://www.tensorflow.org/datasets/overview

Answer 2

您也可以直接从 tf.keras.datasets.mnist.load_data() 获取数据库。

这是代码。

import tensorflow as tf

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

print([i.shape for i in (x_train, y_train, x_test, y_test)])

[(60000, 28, 28), (60000,), (10000, 28, 28), (10000,)]

ModuleNotFoundError：没有名为“ mnist”的模块

2 个答案: