# Neural Networks in Keras

# 1. Sequential Model

from keras.models import Sequential
# Create the Sequential model
model = Sequential()

keras.models.Sequential

# 2. Layers

Layer可以用来向模型添加需要的神经网络层，使用add()函数进行添加：

from keras.models import Sequential
from keras.layers.core import Dense, Activation, Flatten

# Create the Sequential model
model = Sequential()

#1st Layer - Add a flatten layer
model.add(Flatten(input_shape=(32, 32, 3))) #输入32x32x3 输出为3072

#2nd Layer - Add a fully connected layer
model.add(Dense(100)) # 输入为3072 ，输出为100

#3rd Layer - Add a ReLU activation layer
model.add(Activation('relu'))

#4th Layer - Add a fully connected layer
model.add(Dense(60))

#5th Layer - Add a ReLU activation layer
model.add(Activation('relu'))

在Keras中你只需要设定第一层的维度，其他的Keras会自动进行推断。

# 例程

构建神经网络（参考）

model = Sequential()
model.add(Flatten(input_shape=(32, 32, 3)))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(5))
model.add(Activation('softmax'))

# An Alternative Solution
model = Sequential()
model.add(Flatten(input_shape=(32, 32, 3)))
model.add(Dense(128, activation='relu'))
model.add(Dense(5, activation='softmax'))

训练模型

# preprocess data
X_normalized = np.array(X_train / 255.0 - 0.5 )

from sklearn.preprocessing import LabelBinarizer
label_binarizer = LabelBinarizer()
y_one_hot = label_binarizer.fit_transform(y_train)

model.compile('adam', 'categorical_crossentropy', ['accuracy'])
history = model.fit(X_normalized, y_one_hot, epochs=3, validation_split=0.2)

# 3. 卷积神经网络

# 3.1 卷积

from keras.layers.convolutional import Conv2D
...

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(32, 32, 3)))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(5))
model.add(Activation('softmax'))

# 3.2 池化

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(5))
model.add(Activation('softmax'))

# 3.3 Dropout

# Build Convolutional Pooling Neural Network with Dropout in Keras Here
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Dropout(0.5))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(5))
model.add(Activation('softmax'))

# 4. 网络性能评估

• evaluate

metrics = model.evaluate(X_normalized_test, y_one_hot_test)
for metric_i in range(len(model.metrics_names)):
    metric_name = model.metrics_names[metric_i]
    metric_value = metrics[metric_i]
    print('{}: {}'.format(metric_name, metric_value))

20/20 [==============================] - 0s 594us/step
loss: 0.24727313220500946
acc: 0.75