hello! I have a problem, if I have a time sequence whose length is 10. is it possible that i use the model to forecast data? Here are my api:

horizon = 2

models = [NHITS(h=horizon,
               input_size=2*horizon,
               max_steps=50),
         NBEATS(h=horizon,
               input_size=2*horizon,
               max_steps=50),
         TimesNet(h=horizon,
                 input_size=2*horizon,
                 max_steps=50)]

#%%
nf = NeuralForecast(models=models, freq='H')
#%%
a=nf.cross_validation(df=data, step_size=horizon, n_windows=1)

By the way, i wanna know what is mas_Steps, is this iteration times? and what is input_size?

Hello! If you mean train a model on a time series of 10 time steps, I am afraid that's not enough data especially for deep learning. It would be better to use simpler models, maybe a naive forecaster or a statistical model, like ARIMA or exponential smoothing. Otherwise, max_steps is simply the maximum number of iterations used for training. Input size is the length of the input series you feed to the model. In your code block, your model will learn to take twice the horizon to predict a sequence length horizon. In other words, suppose your horizon is 12, then your model is trained to take 24 values as input and output 12 values.