基于Keras的Python实践 10 chapter JSON、YAML模型

keras中，对模型进行序列化的时候，模型权重通常保存在hdf5文件，模型的结构可以保存为json或者yaml文件。

 

1、json模型结构

from sklearn import datasets
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical
from keras.models import model_from_json


# 导入鸢尾花数据
dataset = datasets.load_iris()

x = dataset.data
Y = dataset.target

# Convert labels to categorical one-hot encoding
# 转换成one-shot形式
Y_labels = to_categorical(Y, num_classes=3)

# 设定随机种子
seed = 7
np.random.seed(seed)
# 构建模型函数
def create_model(optimizer='rmsprop', init='glorot_uniform'):
    # 构建模型
    model = Sequential()
    model.add(Dense(units=4, activation='relu', input_dim=4, kernel_initializer=init))
    model.add(Dense(units=6, activation='relu', kernel_initializer=init))
    model.add(Dense(units=3, activation='softmax', kernel_initializer=init))

    # 编译模型
    model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model

# 构建模型
model = create_model()
#verbose=0可以关闭训练过程中的状态输出，比如loss,acc
model.fit(x, Y_labels, epochs=200, batch_size=5, verbose=0)

scores = model.evaluate(x, Y_labels, verbose=0)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))

# 模型保存成Json文件
model_json = model.to_json()
with open('model.json', 'w') as file:
    file.write(model_json)

# 保存模型的权重值
model.save_weights('model.json.h5')


# 从Json加载模型
with open('model.json', 'r') as file:
    model_json = file.read()

# 加载模型权重
new_model = model_from_json(model_json)
new_model.load_weights('model.json.h5')

# 编译模型
# 从json加载模型，加载模型权重后，需要编译模型，才进行模型性能评估
new_model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

# 评估从Json加载的模型
scores = new_model.evaluate(x, Y_labels, verbose=0)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))

2、保存为yaml模型

from sklearn import datasets
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical
from keras.models import model_from_yaml

import os

# TensorFlow的日志级别分为以下三种：
# TF_CPP_MIN_LOG_LEVEL = 1 //默认设置，为显示所有信息
# TF_CPP_MIN_LOG_LEVEL = 2 //只显示error和warining信息
# TF_CPP_MIN_LOG_LEVEL = 3 //只显示error信息

os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"


# 导入鸢尾花数据
dataset = datasets.load_iris()

x = dataset.data
Y = dataset.target

# Convert labels to categorical one-hot encoding
Y_labels = to_categorical(Y, num_classes=3)

# 设定随机种子
seed = 7
np.random.seed(seed)
# 构建模型函数
def create_model(optimizer='rmsprop', init='glorot_uniform'):
    # 构建模型
    model = Sequential()
    model.add(Dense(units=4, activation='relu', input_dim=4, kernel_initializer=init))
    model.add(Dense(units=6, activation='relu', kernel_initializer=init))
    model.add(Dense(units=3, activation='softmax', kernel_initializer=init))

    # 编译模型
    model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model

# 构建模型
model = create_model()
model.fit(x, Y_labels, epochs=200, batch_size=5, verbose=0)

scores = model.evaluate(x, Y_labels, verbose=0)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))

# 模型保存成yaml文件
model_yaml = model.to_yaml()
with open('model.yaml', 'w') as file:
    file.write(model_yaml)

# 保存模型的权重值
model.save_weights('model.yaml.h5')


# 从yaml加载模型
with open('model.yaml', 'r') as file:
    model_yaml = file.read()

# 加载模型
new_model = model_from_yaml(model_yaml)
new_model.load_weights('model.yaml.h5')

# 编译模型
new_model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

# 评估从YAML加载的模型
scores = new_model.evaluate(x, Y_labels, verbose=0)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))

 

3、模型增量更新

为了保证模型的时效性，需要对模型进行增量更新，时间通常为3-6个月。在数据量比较大的时候，若每次采用全部数据

去重新训练模型，时间开销会非常大，因此可以采用增量更新模型的方式对模型进行训练。

在实际应用中，如果采用增量更新，需要与全量更新做对比，以确保增量更新的可行性。

from sklearn import datasets
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical
from keras.models import model_from_json
from sklearn.model_selection import train_test_split

# 设定随机种子
seed = 7
np.random.seed(seed)

# 导入数据
dataset = datasets.load_iris()

x = dataset.data
Y = dataset.target

x_train, x_increment, Y_train, Y_increment = train_test_split(x, Y, test_size=0.2, random_state=seed)

# Convert labels to categorical one-hot encoding
Y_train_labels = to_categorical(Y_train, num_classes=3)


# 构建模型函数
def create_model(optimizer='rmsprop', init='glorot_uniform'):
    # 构建模型
    model = Sequential()
    model.add(Dense(units=4, activation='relu', input_dim=4, kernel_initializer=init))
    model.add(Dense(units=6, activation='relu', kernel_initializer=init))
    model.add(Dense(units=3, activation='softmax', kernel_initializer=init))

    # 编译模型
    model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model

# 构建模型
model = create_model()
model.fit(x_train, Y_train_labels, epochs=10, batch_size=5, verbose=2)

scores = model.evaluate(x_train, Y_train_labels, verbose=0)
print('Base %s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))

# 模型保存成Json文件
model_json = model.to_json()
with open('model.increment.json', 'w') as file:
    file.write(model_json)

# 保存模型的权重值
model.save_weights('model.increment.json.h5')


# 从Json加载模型
with open('model.increment.json', 'r') as file:
    model_json = file.read()

# 加载模型
new_model = model_from_json(model_json)
new_model.load_weights('model.increment.json.h5')

# 编译模型
new_model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

# 增量训练模型
# Convert labels to categorical one-hot encoding
Y_increment_labels = to_categorical(Y_increment, num_classes=3)
new_model.fit(x_increment, Y_increment_labels, epochs=10, batch_size=5, verbose=2)
scores = new_model.evaluate(x_increment, Y_increment_labels, verbose=0)
print('Increment %s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))

4、网络权重检测点

from sklearn import datasets
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical
from keras.callbacks import ModelCheckpoint

# 导入数据
dataset = datasets.load_iris()

x = dataset.data
Y = dataset.target

# Convert labels to categorical one-hot encoding
Y_labels = to_categorical(Y, num_classes=3)

# 设定随机种子
seed = 7
np.random.seed(seed)
# 构建模型函数
def create_model(optimizer='rmsprop', init='glorot_uniform'):
    # 构建模型
    model = Sequential()
    model.add(Dense(units=4, activation='relu', input_dim=4, kernel_initializer=init))
    model.add(Dense(units=6, activation='relu', kernel_initializer=init))
    model.add(Dense(units=3, activation='softmax', kernel_initializer=init))

    # 编译模型
    model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model

# 构建模型
model = create_model()

# 设置检查点
filepath = 'weights-improvement-{epoch:02d}-{val_acc:.2f}.h5'
# 只有在验证集（monitor='val_acc' mode='max'）上分类准确度有所提高时，才会设置检查点保存网络权重
checkpoint = ModelCheckpoint(filepath=filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
callback_list = [checkpoint]
# validation_split=0.2使用自动评估模型，把数据集分割为8:2，并在每一轮epoch后进行验证集验证
# callbacks=callback_list 训练过程中满足条件，会调用callback_list里面对应的函数
model.fit(x, Y_labels, validation_split=0.2, epochs=200, batch_size=5, verbose=0, callbacks=callback_list)

from sklearn import datasets
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical
# keras 的回调函数
from keras.callbacks import ModelCheckpoint

# 导入数据
dataset = datasets.load_iris()

x = dataset.data
Y = dataset.target

# Convert labels to categorical one-hot encoding
Y_labels = to_categorical(Y, num_classes=3)

# 设定随机种子
seed = 7
np.random.seed(seed)
# 构建模型函数
def create_model(optimizer='rmsprop', init='glorot_uniform'):
    # 构建模型
    model = Sequential()
    model.add(Dense(units=4, activation='relu', input_dim=4, kernel_initializer=init))
    model.add(Dense(units=6, activation='relu', kernel_initializer=init))
    model.add(Dense(units=3, activation='softmax', kernel_initializer=init))

    # 编译模型
    model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model

# 构建模型
model = create_model()

# 设置检查点
filepath = 'weights.best.h5'
# 只有在验证集（monitor='val_acc' mode='max'）上分类准确度有所提高时，才会设置检查点保存网络权重
checkpoint = ModelCheckpoint(filepath=filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
callback_list = [checkpoint]
# validation_split=0.2使用自动评估模型，把数据集分割为8:2，并在每一轮epoch后进行验证集验证
# callbacks=callback_list 训练过程中满足条件，会调用callback_list里面对应的函数
model.fit(x, Y_labels, validation_split=0.2, epochs=200, batch_size=5, verbose=0, callbacks=callback_list)

5、模型可视化

from sklearn import datasets
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical
from matplotlib import pyplot as plt


# 导入数据
dataset = datasets.load_iris()

x = dataset.data
Y = dataset.target

# Convert labels to categorical one-hot encoding
Y_labels = to_categorical(Y, num_classes=3)

# 设定随机种子
seed = 7
np.random.seed(seed)
# 构建模型函数
def create_model(optimizer='rmsprop', init='glorot_uniform'):
    # 构建模型
    model = Sequential()
    model.add(Dense(units=4, activation='relu', input_dim=4, kernel_initializer=init))
    model.add(Dense(units=6, activation='relu', kernel_initializer=init))
    model.add(Dense(units=3, activation='softmax', kernel_initializer=init))

    # 编译模型
    model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model

# 构建模型
model = create_model()

history = model.fit(x, Y_labels, validation_split=0.2, epochs=200, batch_size=5, verbose=0)

# 评估模型
scores = model.evaluate(x, Y_labels, verbose=0)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))

# Hisotry列表
# dict_keys(['acc', 'val_loss', 'loss', 'val_acc'])
print(history.history.keys())

# accuracy的历史
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'validation'], loc='upper left')
plt.show()

# loss的历史
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'validation'], loc='upper left')
plt.show()