N-BEATS

N-BEATS copied to clipboard

In the [MASE](https://github.com/ServiceNow/N-BEATS/blob/c746a4f13ffc957487e0c3279b182c3030836053/common/metrics.py#L28), I find that the shapes of `in_sample`, `out_sample`, and `forecasting` should be `time_o` or `time_in`, instead of `batch, time_i/o`. Moreover, does the MASE follow the formulation in...

zezhishao

history_size/window_sampling_limit is shorter than input size

1

For certain datasets, e.g. Yearly/Quarterly/Monthly M4 datasets, the quantity `history_size` is set to 1.5, leading `window_sampling_limit` to be 1.5 times of the horizon length. Yet, the input size could be...

gorold

Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

sachinjm

Hi, In **N-BEATS**, inappropriate dependency versioning constraints can cause risks. Below are the dependencies and version constraints that the project is using ``` gin-config fire matplotlib numpy pandas patool torch...

PyDeps

class GenericBasis(t.nn.Module): """ Generic basis function. """ def __init__(self, backcast_size: int, forecast_size: int): super().__init__() self.backcast_size = backcast_size self.forecast_size = forecast_size def forward(self, theta: t.Tensor): return theta[:, :self.backcast_size], theta[:, -self.forecast_size:] is...

PhoebeChen123

Reproducing M4 Results

1

I am having trouble reproducing the results on the M4 dataset. I am getting the following error when running the notebook for the m4: --------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call...

Cazual

Are there any hyperparameters that are more important than others and do you have recommended ranges? I'm thinking of something similar to this, but for N-BEATS: 

vidarsumo

Hi, I propose that the point forecast of N-BEATS be included in this repo for all the dataset evaluated in the original paper like it has been done for the...

PhilippeChatigny

Instead of parameters with grad=False, buffers is the way to go.

kashif

The only variable as input should be the target which is part of time_varying_unknown_reals

1

My data set has : time_idx, Date, Ticker, Open, high, low, close, Stock split and Dividends. My Time series data set is: training = TimeSeriesDataSet( combined_data[lambda x: x.time_idx

Mohan16071996