Chris Gervais
02/08/2023, 8:54 PMinput_size
to be 0?
`input_size`: int, autorregresive inputs size, y=[1,2,3,4] input_size=2 -> y_[t-2:t]=[1,2].<br>
Farzad E
02/10/2023, 5:21 PMFarzad E
02/10/2023, 7:16 PMChirag Ahuja
02/16/2023, 10:04 AMFarzad E
02/21/2023, 4:49 PMMartin Bel
02/21/2023, 9:19 PMn_pool_kernel_size
and n_freq_downsample
parameters.
Are there any guidelines for this, in relation to the frequency of the series?
It would be great if someone can provide some intuition on how these affect the model.
Would these be reasonable values?
"n_pool_kernel_size": [2, 2, 2], # MaxPooling Kernel size
"n_freq_downsample": [52, 24, 1], # Interpolation expressivity ratios
I'm getting a reasonable result but wanted to see if it's possible to improve. This is an example of the data and predictions.Andrei Tulbure
02/22/2023, 11:14 AMFarzad E
02/22/2023, 9:08 PMFarzad E
02/22/2023, 11:33 PMMartin Bel
02/23/2023, 1:38 PMFarzad E
02/23/2023, 3:06 PMRuntimeError: maximum size for tensor at dimension 2 is 1463 but size is 1825
with 1463 being the size of my time series. The training continues though regardless of this error so I am not sure if this has any negative impact.Manuel
03/18/2023, 8:55 AMManuel
03/21/2023, 5:15 PMDawie van Lill
03/23/2023, 1:54 PMhist_exog_list
and futr_exog_list
components. How would I go about running AutoNHITS with exogenous variables?Mark Aron Szulyovszky
03/23/2023, 3:58 PMMark Aron Szulyovszky
03/23/2023, 3:59 PMinsample_size
when calling predict_rolled to get in_sample predictions?virgilio espina
03/24/2023, 4:33 PMvirgilio espina
03/24/2023, 5:58 PMvirgilio espina
03/24/2023, 6:13 PMMilim Kim
03/27/2023, 8:23 AMvirgilio espina
03/27/2023, 5:19 PMMark Aron Szulyovszky
03/28/2023, 2:51 PMStepLR
doesnβt follow PyTorchβs LRScheduler API. You should override the <http://LightningModule.lr|LightningModule.lr>_scheduler_step
hook with your own logic if you are using a custom LR scheduler.191` while running neuralforecast?
we can run the example locally, but on the CI, it fails.Mark Aron Szulyovszky
03/28/2023, 2:55 PMMark Aron Szulyovszky
03/28/2023, 2:57 PMMark Aron Szulyovszky
03/28/2023, 3:01 PMMark Aron Szulyovszky
03/28/2023, 3:01 PMKaustav Chaudhury
03/31/2023, 4:12 AMMads Jensen
04/03/2023, 9:32 AMOutOfMemoryError: CUDA out of memory.
Is there a parameter to limit that or any recommendations on how to avoid that?Kaustav Chaudhury
04/03/2023, 12:38 PMvirgilio espina
04/03/2023, 4:44 PMfilter_nan_and_inf
arg to False."