文章作者：Tyan
博客：noahsnail.com ?|? CSDN ?|? 簡(jiǎn)書
本文主要介紹Keras的一些基本用法照藻。
- Demo
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Activation, Conv2D, MaxPooling2D, Flatten
from keras.optimizers import Adam
# 加載數(shù)據(jù)集
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# 數(shù)據(jù)集預(yù)處理
X_train = X_train.reshape(-1, 1, 28, 28)
X_test = X_test.reshape(-1, 1, 28, 28)
# 將label變?yōu)橄蛄?y_train = np_utils.to_categorical(y_train, 10)
y_test = np_utils.to_categorical(y_test, 10)
# 構(gòu)建神經(jīng)網(wǎng)絡(luò)
model = Sequential()
# 卷積層一
model.add(Conv2D(32, kernel_size = (5, 5), strides = (1, 1), padding = 'same', activation = 'relu', input_shape = (1, 28, 28)))
# 池化層一
model.add(MaxPooling2D(pool_size = (2, 2), strides = (1, 1), padding = 'same'))
# 卷積層二
model.add(Conv2D(64, kernel_size = (5, 5), strides = (1, 1), padding = 'same', activation = 'relu'))
# 池化層二
model.add(MaxPooling2D(pool_size = (2, 2), strides = (1, 1), padding = 'same'))
# 全連接層一
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation('relu'))
# 全連接層二
model.add(Dense(10))
model.add(Activation('softmax'))
# 選擇并定義優(yōu)化求解方法
adam = Adam(lr = 1e-4)
# 選擇損失函數(shù)凳寺、求解方法鹰服、度量方法
model.compile(optimizer = adam, loss = 'categorical_crossentropy', metrics = ['accuracy'])
# 訓(xùn)練模型
model.fit(X_train, y_train, epochs = 2, batch_size = 32)
# 評(píng)估模型
loss, accuracy = model.evaluate(X_test, y_test)
print ''
print 'loss: ', loss
print 'accuracy: ', accuracy
- 結(jié)果
Using TensorFlow backend.
Epoch 1/2
60000/60000 [==============================] - 55s - loss: 0.4141 - acc: 0.9234
Epoch 2/2
60000/60000 [==============================] - 56s - loss: 0.0743 - acc: 0.9770
9920/10000 [============================>.] - ETA: 0s
loss: 0.103529265788
accuracy: 0.9711
