Skip to content

Commit 2c19c92

Browse files
committed
Some typos fixed - ( added coma to have 60,000 instead of 60 000 - this way the number is not broken into 60 on a line and 000 on the other; fixed intendention in code example)
1 parent 34453d2 commit 2c19c92

1 file changed

Lines changed: 5 additions & 5 deletions

File tree

doc/gettingstarted.txt

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -26,10 +26,10 @@ MNIST Dataset
2626
(`mnist.pkl.gz <http://deeplearning.net/data/mnist/mnist.pkl.gz>`_)
2727

2828
The `MNIST <http://yann.lecun.com/exdb/mnist>`_ dataset consists of handwritten
29-
digit images and it is divided in 60 000 examples for the training set and
30-
10 000 examples for testing. In many papers as well as in this tutorial, the
31-
official training set of 60 000 is divided into an actual training set of 50 000
32-
examples and 10 000 validation examples (for selecting hyper-parameters like
29+
digit images and it is divided in 60,000 examples for the training set and
30+
10,000 examples for testing. In many papers as well as in this tutorial, the
31+
official training set of 60,000 is divided into an actual training set of 50,000
32+
examples and 10,000 validation examples (for selecting hyper-parameters like
3333
learning rate and size of the model). All digit images have been size-normalized and
3434
centered in a fixed size image of 28 x 28 pixels. In the original dataset
3535
each pixel of the image is represented by a value between 0 and 255, where
@@ -60,7 +60,7 @@ MNIST Dataset
6060

6161
.. code-block:: python
6262

63-
import cPickle, gzip, numpy
63+
import cPickle, gzip, numpy
6464

6565
# Load the dataset
6666
f = gzip.open('mnist.pkl.gz','rb')

0 commit comments

Comments
 (0)