A “Hello World” Into Image Recognition with MNIST

MNIST with Keras in Python

To begin, we’ll load the library Keras and other necessary inputs:

import keras 
from keras.datasets 
import mnist from keras.models 
import Sequential from keras.layers 
import Dense, Dropout, Flatten from keras.layers 
import Conv2D, MaxPooling2D 
from keras import backend as K

Next, we’ll load the MNIST dataset and split it into X train, X test, Y train, and Y test data:

(x_train, y_train), (x_test, y_test) = mnist.load_data()

Next, we can outline some important variables for image loading and training.

batch_size = 128 
num_classes = 10 
epochs = 12
img_rows, img_cols = 28, 28

The array must be reshaped and standardized so it can be submitted to Keras:

if K.image_data_format() == 'channels_first':
 x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
 x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
 input_shape = (1, img_rows, img_cols)
else:
 x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
 x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
 input_shape = (img_rows, img_cols, 1)

The data needs to be converted to a 32-bit float and standardized.

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

Since the Y value is from 0 to 9, it must be converted into a categorical state (a vector representing the target value):

y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)

Now that the data is ready, we can define the model architecture.

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
 activation='relu',
 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

After the model architecture has been defined, it must be compiled. Compiling a model outlines the loss function, optimizer, and metrics.

model.compile(loss=keras.losses.categorical_crossentropy,
 optimizer=keras.optimizers.Adadelta(),
 metrics=['accuracy'])

After the model has been defined, the model must be fit with the data.

model.fit(x_train, y_train,
 batch_size=batch_size,
 epochs=epochs,
 verbose=1,
 validation_data=(x_test, y_test))

Keras in Python outputs a progressbar tracking print during training:

The accuracy metric can be called through

score = model.evaluate(x_test, y_test, verbose=0) 
print('Test loss:', score[0]) 
print('Test accuracy:', score[1])

Complete Code

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as Kbatch_size = 128
num_classes = 10
epochs = 12# input image dimensions
img_rows, img_cols = 28, 28# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()if K.image_data_format() == 'channels_first':
 x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
 x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
 input_shape = (1, img_rows, img_cols)
else:
 x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
 x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
 input_shape = (img_rows, img_cols, 1)x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
 activation='relu',
 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))model.compile(loss=keras.losses.categorical_crossentropy,
 optimizer=keras.optimizers.Adadelta(),
 metrics=['accuracy'])model.fit(x_train, y_train,
 batch_size=batch_size,
 epochs=epochs,
 verbose=1,
 validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])