Slackbot
04/11/2022, 9:24 PMCristian (Nixtla)
04/11/2022, 10:00 PMn_windows
equal to the batch size you want. The WindowsDataset will first sample batch_size
series, and then select n_windows
windows from all the constructed windows of the batch_size
series.Kin Gtz. Olivares
04/11/2022, 10:07 PMCristian (Nixtla)
04/11/2022, 10:07 PMn_windows
=batch_size.
.Fabian Müller
04/12/2022, 6:54 AMn_windows
=batch_size
tipp. Will check it out. I also came across the eq_batch_size
argument in the FastTimeSeriesLoader that I am currently using.
But just to be sure, while both methods will result in the number of windows being equal to the batch_size, it is not guaranteed that it will be exactly one window per series. Correct?
And what do you think about the stratified sampling as mentioned in the paper? From what I understand, it might be especially relevant for your approach since you sampling from all windows and long series will produce more windows and therefore will be overrepresented in the training?Kin Gtz. Olivares
04/12/2022, 1:05 PM