Predicting multiple outputs with an LSTM Model

TensorFlow General Discussion
,
1

Hi,

I want to predict multiple outputs with an LSTM Model.
My model works just fine and currently predicts only one output.

(Minimal example in Google Colab)

Please note that I added “output_2” in my Dataframe.
Now I want to predict not only “output” but also “output_2”.
I am aware that the Sequential model is not sufficient for this task.

But I’m asking myself whether there is a simple solution to this problem because I figured it should be quite common to not only predict a single output.

Thanks in advance! :slight_smile:

3

Hello @lucatatas

Thank you for using TensorFlow,

In the code provided through the link, in model definitions model.add(Dense(units=num_outputs)) , num_outputs=2 for multiple outputs. Based on this change, update the data iterator also for multiple outputs, update the output processing and evaluation, so that training would run smoothly, please understand that doing this would increase complexity in training and learning process.