1
$\begingroup$

I am working on a time-series kind of problem. I have (timesteps, features) and the length of output will be (timesteps,). All outputs as float numbers. But the problem is I have training samples with different timesteps. Suppose one example has 1500 timesteps then it will output 1500 dimensional vector. Another example has 1000 timesteps and it will have 1000 dimensional output.

I am looking for a way to train such a model using keras.

$\endgroup$
1
$\begingroup$

Its the number of features that has to remain consistent not the number of timestamps.

Outputs will be batches of one row predictions, so in your case its 1500 and than 1000. Model does not care, features should remain same. And beware of dataleakage with time series.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.