Keras在mnist上的CNN实践，并且自定义loss函数曲线图

使用keras实现CNN，直接上代码：

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K

class LossHistory(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.losses = {'batch':[], 'epoch':[]}
        self.accuracy = {'batch':[], 'epoch':[]}
        self.val_loss = {'batch':[], 'epoch':[]}
        self.val_acc = {'batch':[], 'epoch':[]}

    def on_batch_end(self, batch, logs={}):
        self.losses['batch'].append(logs.get('loss'))
        self.accuracy['batch'].append(logs.get('acc'))
        self.val_loss['batch'].append(logs.get('val_loss'))
        self.val_acc['batch'].append(logs.get('val_acc'))

    def on_epoch_end(self, batch, logs={}):
        self.losses['epoch'].append(logs.get('loss'))
        self.accuracy['epoch'].append(logs.get('acc'))
        self.val_loss['epoch'].append(logs.get('val_loss'))
        self.val_acc['epoch'].append(logs.get('val_acc'))

    def loss_plot(self, loss_type):
        iters = range(len(self.losses[loss_type]))
        plt.figure()
        # acc
        plt.plot(iters, self.accuracy[loss_type], 'r', label='train acc')
        # loss
        plt.plot(iters, self.losses[loss_type], 'g', label='train loss')
        if loss_type == 'epoch':
            # val_acc
            plt.plot(iters, self.val_acc[loss_type], 'b', label='val acc')
            # val_loss
            plt.plot(iters, self.val_loss[loss_type], 'k', label='val loss')
        plt.grid(True)
        plt.xlabel(loss_type)
        plt.ylabel('acc-loss')
        plt.legend(loc="upper right")
        plt.show()

history = LossHistory()

batch_size = 128
nb_classes = 10
nb_epoch = 20
img_rows, img_cols = 28, 28
nb_filters = 32
pool_size = (2,2)
kernel_size = (3,3)
(X_train, y_train), (X_test, y_test) = mnist.load_data()
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 = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

model3 = Sequential()

model3.add(Convolution2D(nb_filters, kernel_size[0] ,kernel_size[1],
                        border_mode='valid',
                        input_shape=input_shape))
model3.add(Activation('relu'))

model3.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model3.add(Activation('relu'))

model3.add(MaxPooling2D(pool_size=pool_size))
model3.add(Dropout(0.25))

model3.add(Flatten())

model3.add(Dense(128))
model3.add(Activation('relu'))
model3.add(Dropout(0.5))

model3.add(Dense(nb_classes))
model3.add(Activation('softmax'))

model3.summary()

model3.compile(loss='categorical_crossentropy',
              optimizer='adadelta',
              metrics=['accuracy'])

model3.fit(X_train, Y_train, batch_size=batch_size, epochs=nb_epoch,
          verbose=1, validation_data=(X_test, Y_test),callbacks=[history])

score = model3.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])

#acc-loss
history.loss_plot('epoch')