Skip to content

Instantly share code, notes, and snippets.

@brendano
Created December 24, 2008 20:11
Show Gist options
  • Save brendano/39760 to your computer and use it in GitHub Desktop.
Save brendano/39760 to your computer and use it in GitHub Desktop.
load the MNIST data set in R
# Load the MNIST digit recognition dataset into R
# http://yann.lecun.com/exdb/mnist/
# assume you have all 4 files and gunzip'd them
# creates train$n, train$x, train$y and test$n, test$x, test$y
# e.g. train$x is a 60000 x 784 matrix, each row is one digit (28x28)
# call: show_digit(train$x[5,]) to see a digit.
# brendan o'connor - gist.github.com/39760 - anyall.org
load_mnist <- function() {
load_image_file <- function(filename) {
ret = list()
f = file(filename,'rb')
readBin(f,'integer',n=1,size=4,endian='big')
ret$n = readBin(f,'integer',n=1,size=4,endian='big')
nrow = readBin(f,'integer',n=1,size=4,endian='big')
ncol = readBin(f,'integer',n=1,size=4,endian='big')
x = readBin(f,'integer',n=ret$n*nrow*ncol,size=1,signed=F)
ret$x = matrix(x, ncol=nrow*ncol, byrow=T)
close(f)
ret
}
load_label_file <- function(filename) {
f = file(filename,'rb')
readBin(f,'integer',n=1,size=4,endian='big')
n = readBin(f,'integer',n=1,size=4,endian='big')
y = readBin(f,'integer',n=n,size=1,signed=F)
close(f)
y
}
train <<- load_image_file('mnist/train-images-idx3-ubyte')
test <<- load_image_file('mnist/t10k-images-idx3-ubyte')
train$y <<- load_label_file('mnist/train-labels-idx1-ubyte')
test$y <<- load_label_file('mnist/t10k-labels-idx1-ubyte')
}
show_digit <- function(arr784, col=gray(12:1/12), ...) {
image(matrix(arr784, nrow=28)[,28:1], col=col, ...)
}
@bob-carpenter
Copy link

Thanks! This saved me quite a bit of spelunking and coding time and the visualizer's really nice.

@chotota
Copy link

chotota commented Jan 25, 2017

hello !!!
well how can i use this in jupyter i mean how can i run this code ...i'm new a little bit on tenserflow and jupyter ... could u plz help me

@javadba
Copy link

javadba commented Feb 3, 2018

In RStudio the data gets loaded (tibble??) but then nothing gets shown. How can we display this?

show_digit <- function(arr784, col=gray(12:1/12), ...) {
image(matrix(arr784, nrow=28)[,28:1], col=col, ...)
}

@medovina
Copy link

medovina commented Feb 6, 2018

@javadba A comment at the top of the code says

# call:  show_digit(train$x[5,])   to see a digit.

Have you tried that? It works for me at the R command line (I'm not using RStudio).

@borislavib
Copy link

@medovina I've tried this in ESS, but when I run the whole file and after that I cannot execute "show_digit(train$x[5,])" in the command line,
It says " Error in matrix(arr784, nrow = 28) : object 'train' not found ", is there any catch in executing the file ? The paths are set.

@sohana08
Copy link

I am using jupyter notebook to run the above code. After calling show_digit function it is showing the following error

Error in matrix(arr784, nrow = 28): object 'train' not found

How do I solve for this

@WhiskersReneeWe
Copy link

works like a charm! Maybe the "catch" here is that you should change the file name "train-images.idx3-ubyte" to "train-images-idx3-ubyte" if you downloaded the data directly from source.

@gao157
Copy link

gao157 commented May 22, 2019

Very nice!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment