Question

我正在尝试使用LSTM预测时间序列。为了减少方差，我尝试使用3个模型进行预测并取3个模型的平均值，这给了我更好的结果。经过培训和验证后，我现在想保存模型以供将来预测。但是，由于我有3种不同的模型，所以我想知道是否有可能将它们合并为一个模型，然后保存/加载它，或者是否应该一一保存所有模型并稍后加载以供将来预测？

# fit 3 models
   model1 = fit_lstm(train_scaled, batch_size,nb_epochs, nb_neurons)
   model2 = fit_lstm(train_scaled, batch_size,nb_epochs, nb_neurons)
   model3 = fit_lstm(train_scaled, batch_size,nb_epochs, nb_neurons)

# predict on test set using 3 models
   forecast1 = model1.predict(test_reshaped, batch_size=batch_size)
   forecast2 = model2.predict(test_reshaped, batch_size=batch_size)
   forecast3 = model3.predict(test_reshaped, batch_size=batch_size)

Answer 1

您正在追求整体模型。

类似以下内容：

askopenfilename

保存整体模型：

from keras.models import load_model
models=[]
for i in range(numOfModels):

    modelTemp=load_model(path2modelx) # load model
    modelTemp.name="aUniqueModelName" # change name to be unique
    models.append(modelTemp)


def ensembleModels(models, model_input):
    # collect outputs of models in a list
    yModels=[model(model_input) for model in models] 
    # averaging outputs
    yAvg=layers.average(yModels) 
    # build model from same input and avg output
    modelEns = Model(inputs=model_input, outputs=yAvg,    name='ensemble')  

    return modelEns



model_input = Input(shape=models[0].input_shape[1:]) # c*h*w
modelEns = ensembleModels(models, model_input)
model.summary()

加载并预测：

modelEns.save(<path_to_model>)

Source

还要选中this article。

将不同的Keras模型合并为一个

1 个答案: