快速开启Keras深度学习之路
1 Keras 序列模型
1.1 添加网络层方法
方法一：
from keras.models import Sequential
from keras.layers import Dense, Activation
model = Sequential([
Dense(32, input_shape=(784,)),
Activation('relu'),
Dense(10),
Activation('softmax'),
])
方法二
from keras.models import Sequential
from keras.layers import Dense, Activation
model = Sequential()#实例化序列模型
model.add(Dense(32, input_dim=784))#添加网络层
model.add(Activation('relu'))#添加激活函数
个人喜欢方法二，逐步添加网络层
1.2 输入shape
在网络层输入的第一层需要输入shape
下列两种方法等效
model = Sequential()
model.add(Dense(32, input_shape=(784,)))
model = Sequential()
model.add(Dense(32, input_dim=784))
1.3 合并Compilation
在训练开始之前需要配置学习过程的参数使用compile(optimize,loss, metrics)
- optimize 优化器名称
- loss 损失函数
- metrics 评估方法
1.3.1 例子
# For a multi-class classification problem
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
# For a binary classification problem
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
# For a mean squared error regression problem
model.compile(optimizer='rmsprop',
loss='mse')
# For custom metrics
import keras.backend as K
def mean_pred(y_true, y_pred):
return K.mean(y_pred)
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy', mean_pred])
1.4 训练过程Training
kesra是基于Numpy数组
1.4.1对单一输入二分类深度学习框架
1.4.1.1 初始化训练模型参数
# For a single-input model with 2 classes (binary classification):
model = Sequential()
model.add(Dense(32, activation='relu', input_dim=100))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
1.4.1.2 创建(加载)数据
# Generate dummy data
import numpy as np
data = np.random.random((1000, 100))
labels = np.random.randint(2, size=(1000, 1))
1.4.1.3开始训练
# Train the model, iterating on the data in batches of 32 samples
model.fit(data, labels, epochs=10, batch_size=32)
1.4.2 对单一输入多分类分类深度学习框架（步骤与上面一致）
# For a single-input model with 10 classes (categorical classification):
model = Sequential()
model.add(Dense(32, activation='relu', input_dim=100))
model.add(Dense(10, activation='softmax'))
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
# Generate dummy data
import numpy as np
data = np.random.random((1000, 100))
labels = np.random.randint(10, size=(1000, 1))
# Convert labels to categorical one-hot encoding
one_hot_labels = keras.utils.to_categorical(labels, num_classes=10)
# Train the model, iterating on the data in batches of 32 samples
model.fit(data, one_hot_labels, epochs=10, batch_size=32)
2 一般深度学习训练过程框架
2.1 多层感知机对多分类的softmax 分类函数
2.1.1 导入包
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.optimizers import SGD
2.1.2 加载数据
# Generate dummy data
import numpy as np
x_train = np.random.random((1000, 20))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(1000, 1)), num_classes=10)
x_test = np.random.random((100, 20))
y_test = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
2.1.3 实例化模型并添加网络层
model = Sequential()
# Dense(64) is a fully-connected layer with 64 hidden units.
# in the first layer, you must specify the expected input data shape:
# here, 20-dimensional vectors.
model.add(Dense(64, activation='relu', input_dim=20))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
2.1.4 整合模型（创建损失函数、优化器、评估函数）
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
2.1.5 开始训练
model.fit(x_train, y_train,
epochs=20,
batch_size=128)
2.1.6 评估训练结果
score = model.evaluate(x_test, y_test, batch_size=128)
2.2 多层感知机对二分类
这里不做解释了（步骤与上述一致）
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout
# Generate dummy data
x_train = np.random.random((1000, 20))
y_train = np.random.randint(2, size=(1000, 1))
x_test = np.random.random((100, 20))
y_test = np.random.randint(2, size=(100, 1))
model = Sequential()
model.add(Dense(64, input_dim=20, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model.fit(x_train, y_train,
epochs=20,
batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)
2.3 VGG-like convnet:可视化几何群网络
百度百科解释
https://baike.baidu.com/item/VGG%20%E6%A8%A1%E5%9E%8B/22689655?fr=aladdin
2.3.1 导入包
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import SGD
2.3.2 创建数据
# Generate dummy data
x_train = np.random.random((100, 100, 100, 3))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
x_test = np.random.random((20, 100, 100, 3))
y_test = keras.utils.to_categorical(np.random.randint(10, size=(20, 1)), num_classes=10)
2.3.3 实例化模型
model = Sequential()
2.3.4 添加网络层
# input: 100x100 images with 3 channels -> (100, 100, 3) tensors.
# this applies 32 convolution filters of size 3x3 each.
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
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(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
2.3.5 整合模型（创建损失函数、优化器、评估函数）
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
2.3.6 训练模型
model.fit(x_train, y_train, batch_size=32, epochs=10)
2.3.7 评估模型
score = model.evaluate(x_test, y_test, batch_size=32)
2.4 使用LSTM（长短期记忆网络）进行序列分类
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import Embedding
from keras.layers import LSTM
max_features = 1024
model = Sequential()
model.add(Embedding(max_features, output_dim=256))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=16, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=16)
2.5 使用1-D卷积进行序列分类
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import Embedding
from keras.layers import Conv1D, GlobalAveragePooling1D, MaxPooling1D
seq_length = 64
model = Sequential()
model.add(Conv1D(64, 3, activation='relu', input_shape=(seq_length, 100)))
model.add(Conv1D(64, 3, activation='relu'))
model.add(MaxPooling1D(3))
model.add(Conv1D(128, 3, activation='relu'))
model.add(Conv1D(128, 3, activation='relu'))
model.add(GlobalAveragePooling1D())
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=16, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=16)
2.6 使用LSTM堆进行序列分类
from keras.models import Sequential
from keras.layers import LSTM, Dense
import numpy as np
data_dim = 16
timesteps = 8
num_classes = 10
# expected input data shape: (batch_size, timesteps, data_dim)
model = Sequential()
model.add(LSTM(32, return_sequences=True,
input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
model.add(LSTM(32, return_sequences=True)) # returns a sequence of vectors of dimension 32
model.add(LSTM(32)) # return a single vector of dimension 32
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# Generate dummy training data
x_train = np.random.random((1000, timesteps, data_dim))
y_train = np.random.random((1000, num_classes))
# Generate dummy validation data
x_val = np.random.random((100, timesteps, data_dim))
y_val = np.random.random((100, num_classes))
model.fit(x_train, y_train,
batch_size=64, epochs=5,
validation_data=(x_val, y_val))
2.7 Same stacked LSTM model, rendered “stateful”
from keras.models import Sequential
from keras.layers import LSTM, Dense
import numpy as np
data_dim = 16
timesteps = 8
num_classes = 10
batch_size = 32
# Expected input batch shape: (batch_size, timesteps, data_dim)
# Note that we have to provide the full batch_input_shape since the network is stateful.
# the sample of index i in batch k is the follow-up for the sample i in batch k-1.
model = Sequential()
model.add(LSTM(32, return_sequences=True, stateful=True,
batch_input_shape=(batch_size, timesteps, data_dim)))
model.add(LSTM(32, return_sequences=True, stateful=True))
model.add(LSTM(32, stateful=True))
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# Generate dummy training data
x_train = np.random.random((batch_size * 10, timesteps, data_dim))
y_train = np.random.random((batch_size * 10, num_classes))
# Generate dummy validation data
x_val = np.random.random((batch_size * 3, timesteps, data_dim))
y_val = np.random.random((batch_size * 3, num_classes))
model.fit(x_train, y_train,
batch_size=batch_size, epochs=5, shuffle=False,
validation_data=(x_val, y_val))
3 源网址
https://keras.io/getting-started/sequential-model-guide/
如果您喜欢我的文章，感觉对您有帮助，不如请问喝杯奶茶,我不怕胖的哦嘻嘻嘻，比心！
