Credits: Forked from deep-learning-keras-tensorflow by Valerio Maggio
Recognize handwritten digits
The MNIST database (link) has a database of handwritten digits.
The training set has $60,000$ samples. The test set has $10,000$ samples.
The digits are size-normalized and centered in a fixed-size image.
The data page has description on how the data was collected. It also has reports the benchmark of various algorithms on the test dataset.
The data is available in the repo's data
folder. Let's load that using the keras
library.
For now, let's load the data and see how it looks.
import numpy as np
import keras
from keras.datasets import mnist
Using Theano backend. Using gpu device 0: GeForce GTX 760 (CNMeM is enabled with initial size: 90.0% of memory, cuDNN 4007)
# Set the full path to mnist.pkl.gz
path_to_dataset = "euroscipy_2016_dl-keras/data/mnist.pkl.gz"
# Load the datasets
(X_train, y_train), (X_test, y_test) = mnist.load_data(path_to_dataset)
Downloading data from https://s3.amazonaws.com/img-datasets/mnist.pkl.gz 15024128/15296311 [============================>.] - ETA: 0s
# What is the type of X_train?
# What is the type of y_train?
# Find number of observations in training data
# Find number of observations in test data
# Display first 2 records of X_train
array([[[0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], ..., [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0]], [[0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], ..., [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0], [0, 0, 0, ..., 0, 0, 0]]], dtype=uint8)
# Display the first 10 records of y_train
array([5, 0, 4, 1, 9, 2, 1, 3, 1, 4], dtype=uint8)
# Find the number of observations for each digit in the y_train dataset
(array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=uint8), array([5923, 6742, 5958, 6131, 5842, 5421, 5918, 6265, 5851, 5949]))
# Find the number of observations for each digit in the y_test dataset
(array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=uint8), array([ 980, 1135, 1032, 1010, 982, 892, 958, 1028, 974, 1009]))
# What is the dimension of X_train?. What does that mean?
(60000, 28, 28)
Let's now display some of the images and see how they look
We will be using matplotlib
library for displaying the image
from matplotlib import pyplot
import matplotlib as mpl
%matplotlib inline
# Displaying the first training data
fig = pyplot.figure()
ax = fig.add_subplot(1,1,1)
imgplot = ax.imshow(X_train[1], cmap=mpl.cm.Greys)
imgplot.set_interpolation('nearest')
ax.xaxis.set_ticks_position('top')
ax.yaxis.set_ticks_position('left')
pyplot.show()
# Let's now display the 11th record