Skip to content

Prediction in real time using Keras #8811

@vasilevskykv

Description

@vasilevskykv

Hi! I would like to ask, does Keras Neural Networks do predictions in real time?
I see, that one of your parameters in prediction is array of data. But when you need to predict future data, you don't have an array of data - you have only previous data and time interval for prediction and nothing more.
As I undestand, you simply checked the prediction because to predict future data I need to give to a function predict a time interval in future, not a previous data trainX as necessary in this function predict

Here is my Neuro Network:
look_back = 3
model = Sequential()
model.add(LSTM(4, input_shape=(look_back, 1)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=20, batch_size=1, verbose=2)
trainPredict = model.predict(trainX)

Can you show an example of predicting in real time?

Metadata

Metadata

Assignees

Type

No type
No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions