CNN on MNIST

In [2]:

from __future__ import print_function
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

batch_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')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

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])

C:\Users\himan\AppData\Local\conda\conda\envs\my_root\lib\site-packages\h5py\__init__.py:34: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
Using TensorFlow backend.

x_train shape: (60000, 28, 28, 1)
60000 train samples
10000 test samples
Train on 60000 samples, validate on 10000 samples
Epoch 1/12
60000/60000 [==============================] - 348s 6ms/step - loss: 0.2738 - acc: 0.9158 - val_loss: 0.0551 - val_acc: 0.9824
Epoch 2/12
60000/60000 [==============================] - 334s 6ms/step - loss: 0.0906 - acc: 0.9738 - val_loss: 0.0411 - val_acc: 0.9862
Epoch 3/12
60000/60000 [==============================] - 339s 6ms/step - loss: 0.0679 - acc: 0.9797 - val_loss: 0.0529 - val_acc: 0.9809
Epoch 4/12
60000/60000 [==============================] - 374s 6ms/step - loss: 0.0557 - acc: 0.9837 - val_loss: 0.0324 - val_acc: 0.9895
Epoch 5/12
60000/60000 [==============================] - 381s 6ms/step - loss: 0.0475 - acc: 0.9853 - val_loss: 0.0312 - val_acc: 0.9894
Epoch 6/12
60000/60000 [==============================] - 383s 6ms/step - loss: 0.0423 - acc: 0.9874 - val_loss: 0.0298 - val_acc: 0.9897
Epoch 7/12
60000/60000 [==============================] - 383s 6ms/step - loss: 0.0384 - acc: 0.9882 - val_loss: 0.0278 - val_acc: 0.9907
Epoch 8/12
60000/60000 [==============================] - 387s 6ms/step - loss: 0.0345 - acc: 0.9892 - val_loss: 0.0270 - val_acc: 0.9906
Epoch 9/12
60000/60000 [==============================] - 388s 6ms/step - loss: 0.0328 - acc: 0.9900 - val_loss: 0.0295 - val_acc: 0.9903
Epoch 10/12
60000/60000 [==============================] - 392s 7ms/step - loss: 0.0305 - acc: 0.9908 - val_loss: 0.0285 - val_acc: 0.9909
Epoch 11/12
60000/60000 [==============================] - 387s 6ms/step - loss: 0.0293 - acc: 0.9908 - val_loss: 0.0294 - val_acc: 0.9909
Epoch 12/12
60000/60000 [==============================] - 387s 6ms/step - loss: 0.0267 - acc: 0.9915 - val_loss: 0.0277 - val_acc: 0.9906
Test loss: 0.027730504500087228
Test accuracy: 0.9906

SHARE

Himanshu Rai

• 
• 
• 
• 
•