score = model.evaluate(X_test, Y_test, verbose=0)

# Keras ������������������import numpy as npnp.random.seed(123)  # ������������������������������������������from keras.models import Sequentialfrom keras.layers import Dense, Dropout, Activation, Flattenfrom keras.layers import Convolution2D, MaxPooling2Dfrom keras.utils import np_utilsfrom keras.datasets import mnistfrom keras import backend as K# ���������������MNIST������������������������������������(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, 28, 28)    X_test = X_test.reshape(X_test.shape[0], 1, 28, 28)    input_shape = (1, 28, 28)else:    X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)    X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)    input_shape = (28, 28, 1)X_train = X_train.astype('float32')X_test = X_test.astype('float32')X_train /= 255X_test /= 255# ������������������Y_train = np_utils.to_categorical(y_train, 10)Y_test = np_utils.to_categorical(y_test, 10)# ������������������model = Sequential()model.add(Convolution2D(32, 3, 3, activation='relu',  input_shape=input_shape))model.add(Convolution2D(32, 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(10, activation='softmax'))# ������������model.compile(loss='categorical_crossentropy',              optimizer='adam',              metrics=['accuracy'])# ������������������������������model.fit(X_train, Y_train,           batch_size=32, nb_epoch=10, verbose=1)# ������������������������������score = model.evaluate(X_test, Y_test, verbose=0)print('Test loss:', score[0])print('Test accuracy:', score[1])

...60000/60000 [==============================] - 148s 2ms/step - loss: 0.2055 - acc: 0.9372Epoch 2/1060000/60000 [==============================] - 131s 2ms/step - loss: 0.0857 - acc: 0.9746Epoch 3/1060000/60000 [==============================] - 128s 2ms/step - loss: 0.0661 - acc: 0.9802Epoch 4/1060000/60000 [==============================] - 120s 2ms/step - loss: 0.0551 - acc: 0.9831Epoch 5/1060000/60000 [==============================] - 124s 2ms/step - loss: 0.0469 - acc: 0.9856Epoch 6/1060000/60000 [==============================] - 134s 2ms/step - loss: 0.0411 - acc: 0.9875Epoch 7/1060000/60000 [==============================] - 120s 2ms/step - loss: 0.0350 - acc: 0.9890Epoch 8/1060000/60000 [==============================] - 117s 2ms/step - loss: 0.0321 - acc: 0.9898Epoch 9/1060000/60000 [==============================] - 123s 2ms/step - loss: 0.0317 - acc: 0.9898Epoch 10/1060000/60000 [==============================] - 122s 2ms/step - loss: 0.0281 - acc: 0.9913Test loss: 0.024244179409698335Test accuracy: 0.9925