--

Deep Learning with Keras

我比较推荐这本书作为参考资料：


同时下列链接也是常用的：
Keras document
Keras 中文文档

Keras 在后台使用 tensorflow 或者 theano 框架，是一种更加高层次的深度学习框架， 可以很容易搭建一个神经网络（当然如果你需要更加定制化以及精细的控制的话，可能 Keras 不一定够了）

1. 利用 Keras 对 MNIST 手写数字识别

Keras MNIST

---

'''Trains a simple convnet on the MNIST dataset.
Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 12

# 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
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (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(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

可以看到 Keras 的神经网络搭建真的非常简单，完全就像搭建积木一样
利用 model.add() 按照 sequence 的顺序，一层又一层， 这个 Sequence 的 model 又提供了接口 fit(), evaluate(), compile() 就像 sklearn 一样。

Keras 提供了各种不同类型的 layer，包括： Dense, Activation, Flatten，Conv2D 等等。 比较关心的是 Conv2D():

keras.layers.Conv2D(
    filters, kernel_size, strides=(1, 1), 
    padding='valid', data_format=None, 
    dilation_rate=(1, 1), 
    activation=None, use_bias=True, 
    kernel_initializer = 'glorot_uniform', 
    bias_initializer = 'zeros', 
    kernel_regularizer = None, 
    bias_regularizer=None, 
    activity_regularizer = None, 
    kernel_constraint = None, 
    bias_constraint=None)

基本上这些参数是很好理解的。

filters: 输出层的层数
kernel_size： 卷积核的大小，比如 (3, 3)
strides： 滑动步长
activation: 默认没有 activation，也可以是 'relu' 或者 'sigmoid'，'tanh' 等等

padding = 'same':
padding means the size of output feature-maps are the same as the input feature-maps (under the assumption of stride=1).
For instance, if input is nin channels with feature-maps of size 28×28, then in the output you expect to get nout feature maps each of size 28×28 as well.

padding = 'valid':
no padding