CODEWITHSUNDEEP
pythonjupytermnist
Theis Hansen
Theis Hansen

Reputation: 53

ModuleNotFoundError: No module named 'mnist'

I am trying to import a locale MNIST dataset from my computer into Jupyter Notebook, but i am getting a ModuleNotFound error.

I have installed the python-mnist package 

# 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'

Upvotes: 3

Views: 11180

Answers (3)

Wreza Shafaghi
Wreza Shafaghi

Reputation: 78

I suppose that you must install

python-mnist

see this link: python-mnist 0.7

Upvotes: 0

Akshay Sehgal
Akshay Sehgal

Reputation: 19322

You can directly fetch the database from tf.keras.datasets.mnist.load_data() as well.

Here is the code for that.

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,)]

Upvotes: 1

Alfredo EP
Alfredo EP

Reputation: 81

Try using:

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

Upvotes: 1

Related Questions