使用预先训练的模型进行Keras时间序列预测

Question

我在Keras中有一个预先设定的时间序列，我也想从一个给定的日期得到一个预测。像这样：

from keras import load_model
def predict(date, filename):
    model = load_model(filename)
    # Do domething to get input_data from date
    return model.predict(input_data)

那怎么办？

Answer 1

您可以通过以下方式保存keras模型

# assume model is the trained keras model
# save the underlying tensorflow graph
model_file = model.to_json()
with open("model.json", "w") as source:
    source.write(model_file)
# save model parameter 
model.save_weights("weights.h5")

然后可以通过

加载保存的模型

from keras.models import model_from_json

with open("model.json", "r") as f:
    model = model_from_json(f.read())
model.load_weights("weights.h5")