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
-2
votes
1 answer

MNIST random sample plotting is not working

I am randomly sampling the MNIST data set, but it shows an error. Where am I doing wrong? import sklearn import pandas as pd import matplotlib.pyplot as plt import numpy as np from sklearn.datasets import fetch_openml mnist =…
-2
votes
2 answers

displaying 100 mnist dataset

This is the code that i am using to print the original unreduced picture of 100 mnist data but is is constantly giving me an error. Even after trying a lot I could not find the solution. Request for suggestion from sklearn.datasets import…
-2
votes
1 answer

How do I implement keras mnist model with video camera

I have successfully build an model of handwritten digits. How would I load the model and use it with live data coming from a video camera? I would like it to draw a box around the number and label the number.
-2
votes
1 answer

Output of a neural network

I test my network with the mnist dataset. Therefore the output of the model has shape 10. How do I reshape the output? For example, if the output is label 3, is then the output [0 0 0 1 0 0 0 0 0 0], or [0 0 0 3 0 0 0 0 0 0] or completely…
gab
  • 165
  • 2
  • 8
-2
votes
1 answer

tensorflow multi label classification mnist

I am trying to do a sequence detection on the mnist dataset. I would like to do this without RNNs. In order to do so I horizontally stacked (up to)5 images to a sequence and then run the classification on it. However it does not work that well as I…
b4shyou
  • 187
  • 1
  • 1
  • 7
-2
votes
1 answer

How to combine Keras MNIST dataset with my own MNIST images?

I created some MNIST digits by using a generative adversarial neural network and saved them in png format. I know that Keras has the MNIST dataset, but I want to combine the digit images that I created with the original MNIST dataset in the Keras.…
-2
votes
1 answer

ResourceExhaustedError when trying to train with MNIST

I am getting ResourceExhaustedError when trying to train MNIST I found out that I can change the batch size in order to avoid the problem, but unfortunately I dont know where to do that in my code Traceback: ResourceExhaustedError (see above for…
mrk
  • 99
  • 3
  • 12
-2
votes
1 answer

Tensorflow download_and_convert_mnist_m.py No such file or directory: '~/dsn_data/mnist_m/mnist_m_train'

I have a weird error message using the download_and_convert_mnist_m.py script from github https://github.com/tensorflow/models/tree/master/research/domain_adaptation/datasets. The command I am using from the models/research/ folder is python…
HutzelFutzel
  • 187
  • 1
  • 2
  • 10
-2
votes
1 answer

Loading own dataset like MNIST images

I am trying to load my own hand written images and test them in my MNIST model. But, i need to pre process the images first. I have 100 images, 10 of every 10 digits saved on the folder images. I am getting error and i don't know if this code works.…
emma19
  • 57
  • 2
  • 7
-2
votes
1 answer

when using CNN ,to_categorical()wrong

use CNN for handwritten digit.
代朝阳
  • 1
  • 2
-2
votes
1 answer

Error ord() in python

To begin my study about neural network I try to learn about mnist dataset. I learn from http://yann.lecun.com/exdb/mnist/ website. Then I want to try convert the dataset into csv file. As I know there are csv files on the internet, but I want to try…
dev-x
  • 897
  • 3
  • 15
  • 30
-2
votes
1 answer

Why InfMnist (MNIST) size of 8M examples is calculated as 8 109 999 examples?

On the website : http://leon.bottou.org/projects/infimnist It says : Generating files containing the MNIST8M training set: $ infimnist lab 10000 8109999 > mnist8m-labels-idx1-ubyte $ infimnist pat 10000 8109999 > mnist8m-patterns-idx3-ubyte However,…
KenobiBastila
  • 539
  • 4
  • 16
  • 52
-3
votes
1 answer

Why is my neural network stagnating around a certain cost?

I am making a neural network that's supposed to be capable of identifying handwritten numbers using the Mnist database downloadable here. The network works perfectly with one to 5 examples but after 10 it starts to get a bit iffy. Using a standard…
-3
votes
1 answer

MNIST: gets lower accuracy than the results I see on the internet

I am trying to train a fully connected neural network to classify hand-written number using MNIST datasets. The neural network is implemented by me in C++. This is part of my course project. However, I find the training is somehow weird. I do not…
Ronghao
  • 1
  • 2
-3
votes
1 answer

Neural Network MNIST number recognition

I recently tried to create my first project with Neural Networks and that's what i came up with. I wanted to make it recognize MNIST handwritten numbers. The problem is, when i run this code and make it train like ~400k times i get ~28% of accuracy…
Wiktor
  • 885
  • 1
  • 9
  • 23
1 2 3
88
89