Stack Overflow
Stack Overflow

Questions tagged [mnist]

MNIST is a database of handwritten digits collected by Yann Lecun and widely used in machine learning research.

MNIST is a database of handwritten digits collected by Yann Lecun, a famous computer scientist, when he was working at AT&T-Bell Labs on the problem of automation of check readings for banks. The data set is a benchmark widely used in machine learning research. Due to its small size it is also widely used for educational purposes.

Here is the full documentation for MNIST database of handwritten digits:

It is a good database for people who want to try learning techniques and pattern recognition methods on real-world data while spending minimal efforts on preprocessing and formatting.

1329 questions
10
votes
4 answers

jupyter notebook's kernel keeps dying when I run the code

I made my first steps in deep learning by following this tutorial, and everything was going well until I needed to train the network in jupyter notebook. I tried almost everything and I always get this error The kernel appears to have died. It will…
Matija
  • 493
  • 4
  • 9
  • 21
10
votes
2 answers

How to download MNIST images as PNGs

I want to download the MNIST images to my computer as PNG files. I found this page: http://yann.lecun.com/exdb/mnist/ After I pressed: train-images-idx3-ubyte.gz: training set images (9912422 bytes) Please let me know if you have any ideas or…
user11141180
10
votes
3 answers

Keras - Save image embedding of the mnist data set

I've written the following simple MLP network for the MNIST db. from __future__ import print_function import keras from keras.datasets import mnist from keras.models import Sequential from keras.layers import Dense, Dropout from keras import…
Shlomi Schwartz
  • 8,693
  • 29
  • 109
  • 186
10
votes
1 answer

Tensorflow - Testing a mnist neural net with my own images

I'm trying to write a script that will allow me to draw an image of a digit and then determine what digit it is with a model trained on MNIST. Here is my code: import random import image from tensorflow.examples.tutorials.mnist import…
Vincent Cloutier
  • 331
  • 2
  • 11
10
votes
4 answers

R - Image Plot MNIST dataset

My data set is the MNIST from Kaggle I am trying to use the image function to visualise say the first digit in the training set. Unfortunately I am getting the following error: >image(1:28, 1:28, im, col=gray((0:255)/255)) Error in…
Anurag H
  • 909
  • 11
  • 28
9
votes
2 answers

Error: from tensorflow.examples.tutorials.mnist import input_data

My environment is as follows: * Windows 7, 64 bit * Anaconda Navigator 1.8.7 * python 3.6.5 * tensorflow 1.8.0 In python, I type: import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data i got error as follows: >>> from…
sliawatimena
  • 338
  • 1
  • 4
  • 16
9
votes
1 answer

How do I merge two trained neural network weight matrices into one?

I have two identical neural networks running on two separate computers (to reduce the time taken to train the network), each having a subset of a complete data set (MNIST). My question is; can I combine the two weight matrices of both networks into…
Gerrit Luimstra
  • 522
  • 6
  • 23
9
votes
2 answers

Why do we flatten the data before we feed it into tensorflow?

I'm following udacity MNIST tutorial and MNIST data is originally 28*28 matrix. However right before feeding that data, they flatten the data into 1d array with 784 columns (784 = 28 * 28). For example, original training set shape was (200000, 28,…
aerin
  • 20,607
  • 28
  • 102
  • 140
9
votes
4 answers

Parsing Yann LeCun's MNIST IDX file format

I would like to understand how to open this version of the MNIST data set. For example, the training set label file train-labels-idx1-ubyte is defined as: TRAINING SET LABEL FILE (train-labels-idx1-ubyte): [offset] [type] [value] …
jds
  • 7,910
  • 11
  • 63
  • 101
9
votes
3 answers

Pre-processing before digit recognition for NN & CNN trained with MNIST dataset

I'm trying to classify handwriting digits, written by myself and a few friends, by usign NN and CNN. In order to train the NN, MNIST dataset is used. The problem is the NN trained with MNIST dataset does not give satisfying test results on my…
yasin.yazici
  • 275
  • 1
  • 2
  • 12
9
votes
3 answers

Are there similar datasets to MNIST?

I am doing research on machine learning. Now I want to test my algorithms with some famous datasets. Since I am a newbie in this area, I can't find other suitable datasets apart from MNIST. I thing MNIST is quite suitable for our research. Does…
Nothing More
  • 873
  • 12
  • 29
8
votes
3 answers

Improve real-life results of neural network trained with mnist dataset

I've built a neural network with keras using the mnist dataset and now I'm trying to use it on photos of actual handwritten digits. Of course I don't expect the results to be perfect but the results I currently get have a lot of room for…
Johanna
  • 143
  • 1
  • 10
8
votes
4 answers

Cross validation for MNIST dataset with pytorch and sklearn

I am new to pytorch and are trying to implement a feed forward neural network to classify the mnist data set. I have some problems when trying to use cross-validation. My data has the following shapes: x_train: torch.Size([45000, 784]) and y_train:…
Kimmen
  • 183
  • 1
  • 1
  • 8
8
votes
1 answer

How to prepare my own data for tensorflow?

I install Tensorflow on ubuntu 14.04. I completed MNIST For ML Beginners tutorial. I understood it. Nor, I try to use my own data. I have train datas as T[1000][10]. Labels are L[2], 1 or 0. How can I access my data mnist.train.images ?
user2362956
8
votes
1 answer

Theano CUDA exception

I'm relatively new to theano and I want to run the mnist example on my GPU but I get the following output: Using gpu device 0: GeForce GTX 970M (CNMeM is disabled) Loading data... Building model and compiling functions... WARNING…
Tim
  • 445
  • 5
  • 19
1 2
3
…
88 89