Open dorienh opened 3 years ago
hop_size??
I know about hop_size
in audio processing but in Timeseries. Can you let me know what do you mean by hop_size here?
My bad, By mistake I closed the issue
I have a feeling, I could be wrong, that the data is currently processed as follows:
1 2 3 4 5 6 7 8 9 10 ...
with a last_x_days = 3
inputs are: 1 2 3 -> predict at 4 4 5 6 -> predict at 7 7 8 9 -> predict at 10
instead of:
1 2 3 -> 4 2 3 4 -> 5 3 4 5 -> 6 4 5 6 -> 7 ...
Does that clarify a bit?
On Fri, 4 Jun 2021 at 15:20, Gyanendra Das @.***> wrote:
My bad, By mistake I closed the issue
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/dorienh/jesse/issues/13#issuecomment-854430898, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABEES6Z2UPUK5VM5OS2PPYLTRB5C5ANCNFSM454A2T5Q .
-- Dorien Herremans, PhD Assistant Professor, ISTD & DAI Director, SUTD Game Lab Lead, AMAAI (Audio, Music and AI Lab) http://dorienherremans.com
Singapore University of Technology and Design Information Technology and Design Pillar Office 1.502-18
Yeah I got it. I hope I did something wrong in input, I will check it
I have a suspicion that the hop size > 1 in the data preloading.
Can we check that hope size = 1?
Examining the X_train tensors it does not seem like they are hopped. But maybe I am missing something and it's randomized.
Which there were comments in this class!