Closed paularindam closed 3 years ago
As of Jan 18th 2021, the pip libraries are broken and give TypeErrors when building NbeatsNet.GENERIC_BLOCKS
WORKAROUND: uninstall the libraries from pip (pip uninstall nbeats-keras
or pip uninstall nbeats-torch
), and copy-paste the nbeats_pytorch
folder in the repo on the directory where your code is (as this bug does not exist in the GitHub version).
I updated the code and pushed the new versions on pip so it should work properly now.
(I pushed the nbeats 1.3.3 version that should solve this).
pip install nbeats-pytorch --upgrade
pip install nbeats-keras --upgrade
I am getting error when running this example when running NBeats.ipynb while running the following command. If I remove stack_types or set it as ('trend','seasonality') it works fine. But it gives error with GENERIC_BLOCK
net = NBeatsNet(device=device, stack_types=(NBeatsNet.GENERIC_BLOCK, NBeatsNet.GENERIC_BLOCK), forecast_length=forecast_length, backcast_length=backcast_length, hidden_layer_units=128, share_weights_in_stack=False, )
Error Statement
TypeError Traceback (most recent call last)