99 lines
2.9 KiB
Python
99 lines
2.9 KiB
Python
"""
|
|
This is a modified version of the Keras mnist example.
|
|
https://keras.io/examples/mnist_cnn/
|
|
|
|
Instead of using a fixed number of epochs this version continues to train
|
|
until the stop criteria is reached.
|
|
|
|
Model performance should be around 99.4% after training.
|
|
|
|
|
|
This scripts shows how to correctly handle mnist data
|
|
and how to use it for the model.fit() function
|
|
"""
|
|
|
|
from __future__ import print_function
|
|
import keras
|
|
from keras.datasets import mnist
|
|
from keras.layers import Conv2D, MaxPooling2D, BatchNormalization, Activation
|
|
from keras import backend as K
|
|
from keras.callbacks import ModelCheckpoint, EarlyStopping
|
|
from keras.models import Model
|
|
from keras.layers import Input, Flatten, Dense
|
|
|
|
batch_size = 128
|
|
num_classes = 10
|
|
epochs = 999999
|
|
|
|
# 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
|
|
|
|
y_train = keras.utils.to_categorical(y_train, num_classes)
|
|
y_test = keras.utils.to_categorical(y_test, num_classes)
|
|
|
|
|
|
def create_base_network(input_shape):
|
|
input = Input(shape=input_shape)
|
|
x = Conv2D(32, kernel_size=(3, 3),
|
|
input_shape=input_shape)(input)
|
|
x = BatchNormalization()(x)
|
|
x = Activation(activation='relu')(x)
|
|
x = MaxPooling2D(pool_size=(2, 2))(x)
|
|
x = Conv2D(64, kernel_size=(3, 3))(x)
|
|
x = BatchNormalization()(x)
|
|
x = Activation(activation='relu')(x)
|
|
x = MaxPooling2D(pool_size=(2, 2))(x)
|
|
x = Flatten()(x)
|
|
x = Dense(128)(x)
|
|
x = BatchNormalization()(x)
|
|
x = Activation(activation='relu')(x)
|
|
x = Dense(num_classes)(x)
|
|
x = BatchNormalization()(x)
|
|
x = Activation(activation='softmax')(x)
|
|
return Model(input, x)
|
|
|
|
|
|
model = create_base_network(input_shape)
|
|
model.compile(loss=keras.losses.categorical_crossentropy,
|
|
optimizer=keras.optimizers.adam(),
|
|
metrics=['accuracy'])
|
|
|
|
checkpoint_path = "./checkpoint"
|
|
|
|
callbacks = [
|
|
EarlyStopping(monitor='val_acc', patience=10, verbose=0),
|
|
ModelCheckpoint(checkpoint_path,
|
|
monitor='val_acc',
|
|
save_best_only=True,
|
|
verbose=0)
|
|
]
|
|
model.fit(x_train, y_train,
|
|
batch_size=batch_size,
|
|
epochs=epochs,
|
|
verbose=1,
|
|
callbacks=callbacks,
|
|
validation_data=(x_test, y_test))
|
|
|
|
model.load_weights(checkpoint_path)
|
|
|
|
score = model.evaluate(x_test, y_test, verbose=0)
|
|
print('Test loss:', score[0])
|
|
print('Test accuracy:', score[1])
|