Python 用于神经网络的 Keras 模型 load_weights
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/41859997/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Keras model load_weights for Neural Net
提问by Deadulus
I'm using the Keras library to create a neural network in python. I have loaded the training data (txt file), initiated the network and "fit" the weights of the neural network. I have then written code to generate the output text. Here is the code:
我正在使用 Keras 库在 python 中创建一个神经网络。我已经加载了训练数据（txt 文件），启动了网络并“拟合”了神经网络的权重。然后我编写了代码来生成输出文本。这是代码：
#!/usr/bin/env python
# load the network weights
filename = "weights-improvement-19-2.0810.hdf5"
model.load_weights(filename)
model.compile(loss='categorical_crossentropy', optimizer='adam')
My problem is: on execution the following error is produced:
我的问题是：在执行时产生以下错误：
model.load_weights(filename)
NameError: name 'model' is not defined
I have added the following but the error still persists:
我添加了以下内容，但错误仍然存在：
from keras.models import Sequential
from keras.models import load_model
Any help would be appreciated.
任何帮助，将不胜感激。
回答by ShmulikA
you need to first create the network object called model, compile it and only after call the model.load_weights(fname)
您需要首先创建名为 的网络对象model，编译它，然后才调用model.load_weights(fname)
working example:
工作示例：
from keras.models import Sequential
from keras.layers import Dense, Activation
def build_model():
model = Sequential()
model.add(Dense(output_dim=64, input_dim=100))
model.add(Activation("relu"))
model.add(Dense(output_dim=10))
model.add(Activation("softmax"))
# you can either compile or not the model
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
return model
model1 = build_model()
model1.save_weights('my_weights.model')
model2 = build_model()
model2.load_weights('my_weights.model')
# do stuff with model2 (e.g. predict())
Save & Load an Entire Model
保存和加载整个模型
in Keras we can save & load the entire model like this (more info here):
在 Keras 中，我们可以像这样保存和加载整个模型（更多信息在这里）：
from keras.models import load_model
model1 = build_model()
model1.save('my_model.hdf5')
model2 = load_model('my_model.hdf5')
# do stuff with model2 (e.g. predict()
