- 需要安装h5py:
pip install h5py
1.模型的保存与加载
- 方法1:model.save()
model.save('model_path.h5')
# 保存模型
model = load_model('model_path.h5')
# 加载模型, 需要from keras.models import load_model
说明: - 方法2:model.save_weights()
model.save_weights('model_path.h5')
# 保存模型权重
model.load_weights('model_path.h5')
# 加载模型权重
说明:需要先把模型定义出来,然后再加载权值。 - 方法3和方法4:model.to_json()和model.to_yaml()
本人使用的不多,可以参考:Keras模型保存的几个方法和它们的区别
或者keras的官网:Model saving & serialization APIs
2.代码案例
保存模型
import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
# (60000,28,28)
print('x_shape:',x_train.shape)
# (60000)
print('y_shape:',y_train.shape)
# (60000,28,28)->(60000,784)
x_train = x_train.reshape(x_train.shape[0],-1)/255.0
x_test = x_test.reshape(x_test.shape[0],-1)/255.0
# 换one hot格式
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)
# 创建模型,输入784个神经元,输出10个神经元
model = Sequential([
Dense(units=10,input_dim=784,bias_initializer='one',activation='softmax')
])
# 定义优化器
sgd = SGD(lr=0.2)
# 定义优化器,loss function,训练过程中计算准确率
model.compile(
optimizer = sgd,
loss = 'mse',
metrics=['accuracy'],
)
# 训练模型
model.fit(x_train,y_train,batch_size=64,epochs=5)
# 评估模型
loss,accuracy = model.evaluate(x_test,y_test)
print('\ntest loss',loss)
print('accuracy',accuracy)
# 保存模型
model.save('model.h5') # HDF5文件,pip install h5py
加载模型
import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
from keras.models import load_model
# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
# (60000,28,28)
print('x_shape:',x_train.shape)
# (60000)
print('y_shape:',y_train.shape)
# (60000,28,28)->(60000,784)
x_train = x_train.reshape(x_train.shape[0],-1)/255.0
x_test = x_test.reshape(x_test.shape[0],-1)/255.0
# 换one hot格式
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)
# 载入模型
model = load_model('model.h5')
# 评估模型
loss,accuracy = model.evaluate(x_test,y_test)
print('\ntest loss',loss)
print('accuracy',accuracy)
在原有模型的基础上,再迭代训练两个周期,以提高精确度
# 训练模型
model.fit(x_train,y_train,batch_size=64,epochs=2)
# 评估模型
loss,accuracy = model.evaluate(x_test,y_test)
print('\ntest loss',loss)
print('accuracy',accuracy)
- 保存模型的参数或者保存模型的网络结构
# 保存参数,载入参数
model.save_weights('my_model_weights.h5')
model.load_weights('my_model_weights.h5')
# 保存网络结构,载入网络结构
from keras.models import model_from_json
json_string = model.to_json()
model = model_from_json(json_string)
print(json_string)
参考:
视频: 覃秉丰老师的“Keras入门”:http://www.ai-xlab.com/course/32
博客参考:https://www.cnblogs.com/XUEYEYU/tag/keras%E5%AD%A6%E4%B9%A0/