import numpy as np
np.random.seed(1337) # for reproducibility
from tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets('MNIST_data',one_hot=False)
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense, Activation, Convolution2D, MaxPooling2D, Flatten
from keras.optimizers import Adam
X_train,y_train,X_test,y_test=mnist.train.images,mnist.train.labels,mnist.test.images,mnist.test.labels
# data pre-processing
X_train = X_train.reshape(-1, 1,28, 28)/255.
X_test = X_test.reshape(-1, 1,28, 28)/255.
y_train = np_utils.to_categorical(y_train, num_classes=10)
y_test = np_utils.to_categorical(y_test, num_classes=10)
# Another way to build your CNN
model = Sequential()
# 卷积层 Conv layer 1 output shape (32, 28, 28)
model.add(Convolution2D(
batch_input_shape=(None, 1, 28, 28), #多少数据 通道数 宽 高
filters=32, #滤波器数量
kernel_size=5, #滤波器大小5x5
strides=1, #步长1
padding='same', # Padding method
data_format='channels_first',
))
model.add(Activation('relu'))
# 池化 Pooling layer 1 (max pooling) output shape (32, 14, 14)
model.add(MaxPooling2D(
pool_size=2, #卷积核大小
strides=2, #卷积步长
padding='same', # Padding method
data_format='channels_first',
))
# Conv layer 2 output shape (64, 14, 14)
model.add(Convolution2D(64, 5, strides=1, padding='same', data_format='channels_first'))
model.add(Activation('relu'))
# Pooling layer 2 (max pooling) output shape (64, 7, 7)
model.add(MaxPooling2D(2, 2, 'same', data_format='channels_first'))
# Fully connected layer 1 input shape (64 * 7 * 7) = (3136), output shape (1024)
model.add(Flatten()) #将数据抹平为一维
model.add(Dense(1024)) #接入全链接层
model.add(Activation('relu'))
# Fully connected layer 2 to shape (10) for 10 classes
model.add(Dense(10))
model.add(Activation('softmax'))
# Another way to define your optimizer
adam = Adam(lr=1e-4)
# We add metrics to get more results you want to see
model.compile(optimizer=adam,
loss='categorical_crossentropy',
metrics=['accuracy'])
print('Training ------------')
# Another way to train the model
model.fit(X_train, y_train, epochs=3, batch_size=64,)
print('\nTesting ------------')
# Evaluate the model with the metrics we defined earlier
loss, accuracy = model.evaluate(X_test, y_test)
print('\ntest loss: ', loss)
print('\ntest accuracy: ', accuracy)
2. 二维卷积层Conv2D
keras.layers.convolutional.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)
二维卷积层对二维输入进行滑动窗卷积,当使用该层作为第一层时,应提供input_shape
参数。
filters:卷积核的数目;
kernel_size:卷积核的尺寸;
strides:卷积核移动的步长,分为行方向和列方向;
padding:边界模式,有“valid”,“same”或“full”,full需要以theano为后端;
其他参数请参看Keras官方文档。
3. 二维池化层MaxPooling2D
keras.layers.pooling.MaxPooling2D(pool_size=(2,2), strides=None, padding='valid', data_format=None)
对空域信号进行最大值池化。
pool_size:池化核尺寸;
strides:池化核移动步长;
padding:边界模式,有“valid”,“same”或“full”,full需要以theano为后端;
其他参数请参看Keras官方文档。
4. Activation层
keras.layers.core.Activation(activation)
激活层对一个层的输出施加激活函数。
预定义激活函数:
softmax,softplus,softsign,relu,tanh,sigmoid,hard_sigmoid,linear等。
5. Dropout层
keras.layers.core.Dropout(p)
为输入数据施加Dropout。Dropout将在训练过程中每次更新参数时随机断开一定百分比(p)的输入神经元连接,Dropout层用于防止过拟合。
6. Flatten层
keras.layers.core.Flatten()
Flatten层用来将输入“压平”,即把多维的输入一维化,常用在从卷积层到全连接层的过渡。Flatten不影响batch的大小。
例子:
model =Sequential()
model.add(Convolution2D(64,3, 3, border_mode='same', input_shape=(3, 32, 32)))
# now:model.output_shape == (None, 64, 32, 32)
model.add(Flatten())
# now:model.output_shape == (None, 65536)
7.Dense层全连接层
keras.layers.core.Dense(units,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)
units:输出单元的数量,即全连接层神经元的数量,作为第一层的Dense层必须指定input_shape。
8. Sequential模型compile方法
compile(self,optimizer, loss, metrics=[], sample_weight_mode=None)
编译用来配置模型的学习过程,其参数有:
optimizer:字符串(预定义优化器名)或优化器对象;
loss:字符串(预定义损失函数名)或目标函数;
metrics:列表,包含评估模型在训练和测试时的网络性能的指标,典型用法是metrics=['accuracy'];
9. Sequential模型fit方法
fit(self,x, y, batch_size=32, epochs=10, verbose=1, callbacks=None,validation_split=0.0, validation_data=None, shuffle=True, class_weight=None,sample_weight=None, initial_epoch=0)
verbose:日志显示,0为不在标准输出流输出日志信息,1为输出进度条记录,2为每个epoch输出一行记录;
validation_split:0~1之间的浮点数,用来指定训练集的一定比例数据作为验证集。验证集将不参与训练,并在每个epoch结束后测试的模型的指标,如损失函数、精确度等;
validation_data:形式为(X,y)的tuple,是指定的验证集。此参数将覆盖validation_spilt。
10. Sequential模型evaluate方法
evaluate(self,x, y, batch_size=32, verbose=1, sample_weight=None)
相关参数可参考其他方法的同名参数说明。