python simple convolutional neural network for MNIST dataset

Posted on | Edited on | In

description: simple CNN example for MNIST dataset

import packages

1
2
3
4
5
6
7
8
9
10
11
import numpy
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
K.set_image_dim_ordering('th')

fix random seed for reproducibility

1
2
seed = 7
numpy.random.seed(seed)

load data

1
2
3
4
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).astype('float32')

normalize inputs from 0-255 to 0-1

1
2
3
4
5
6
X_train = X_train / 255
X_test = X_test / 255
# one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]

define baseline model

1
2
3
4
5
6
7
8
9
10
11
12
def baseline_model():
	# create model
	model = Sequential()
	model.add(Conv2D(32, (5, 5), input_shape=(1, 28, 28), activation='relu'))
	model.add(MaxPooling2D(pool_size=(2, 2)))
	model.add(Dropout(0.2))
	model.add(Flatten())
	model.add(Dense(128, activation='relu'))
	model.add(Dense(num_classes, activation='softmax'))
	# Compile model
	model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
	return model

define model

1
2
3
4
5
6
7
# build the model
model = baseline_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=3, batch_size=200, verbose=2)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Baseline Error: %.2f%%" % (100-scores[1]*100))

output

1
2
3
4
5
6
7
8
9
10
11
Train on 60000 samples, validate on 10000 samples

Epoch 1/3

69s - loss: 0.2498 - acc: 0.9283 - val_loss: 0.0715 - val_acc: 0.9803

Epoch 2/3

70s - loss: 0.0714 - acc: 0.9786 - val_loss: 0.0503 - val_acc: 0.9833

Epoch 3/3