Move tensors to correct device

[karl-richter]

Resolves #1002

Initially we assumed that with Lightning we do not have to worry about moving tensors to devices at all, but it turns out that this assumption only holds for tensor created via the data loaders. All manually created tensors need to be moved to the correct device (which is very straight forward in Lightning due to the self.device arg, Reference).

Adds a pytest that uses an accelerator if available. On github action workers, accelerators are most likely not available, but on local machines this could help detect issues early.

[github-actions]

98c867c

Model Benchmark

Benchmark	Metric	main	current	diff
YosemiteTemps	MAE_val	1.72948	1.72949	0.0%	✅
YosemiteTemps	RMSE_val	2.27386	2.27386	0.0%	✅
YosemiteTemps	Loss_val	0.00096	0.00096	0.0%	✅
YosemiteTemps	RegLoss_val	0	0	0.0%	✅
YosemiteTemps	epoch	84	84	0.0%	✅
YosemiteTemps	MAE	1.45189	1.45189	0.0%	✅
YosemiteTemps	RMSE	2.16631	2.16631	0.0%	✅
YosemiteTemps	Loss	0.00066	0.00066	0.0%	✅
YosemiteTemps	RegLoss	0	0	0.0%	✅
YosemiteTemps	time	153.57	108.37	-29.43%	✅
PeytonManning	MAE_val	0.64636	0.64636	0.0%	✅
PeytonManning	RMSE_val	0.79276	0.79276	0.0%	✅
PeytonManning	Loss_val	0.01494	0.01494	0.0%	✅
PeytonManning	RegLoss_val	0	0	0.0%	✅
PeytonManning	epoch	37	37	0.0%	✅
PeytonManning	MAE	0.42701	0.42701	0.0%	✅
PeytonManning	RMSE	0.57032	0.57032	0.0%	✅
PeytonManning	Loss	0.00635	0.00635	0.0%	✅
PeytonManning	RegLoss	0	0	0.0%	✅
PeytonManning	time	18.97	12.85	-32.26%	✅
AirPassengers	MAE_val	15.2698	15.2698	0.0%	✅
AirPassengers	RMSE_val	19.4209	19.4209	0.0%	✅
AirPassengers	Loss_val	0.00195	0.00195	0.0%	✅
AirPassengers	RegLoss_val	0	0	0.0%	✅
AirPassengers	epoch	89	89	0.0%	✅
AirPassengers	MAE	9.82902	9.82902	0.0%	✅
AirPassengers	RMSE	11.7005	11.7005	0.0%	✅
AirPassengers	Loss	0.00056	0.00056	0.0%	✅
AirPassengers	RegLoss	0	0	0.0%	✅
AirPassengers	time	7.18	5.45	-24.09%	✅

Model training plots

Model Training

PeytonManning

YosemiteTemps

AirPassengers

[codecov-commenter]

Codecov Report

Merging #1010 (d0fe10d) into main (499ae1a) will increase coverage by 0.10%.
The diff coverage is 84.61%.

@@            Coverage Diff             @@
##             main    #1010      +/-   ##
==========================================
+ Coverage   89.89%   89.99%   +0.10%     
==========================================
  Files          19       19              
  Lines        4659     4659              
==========================================
+ Hits         4188     4193       +5     
+ Misses        471      466       -5     

Impacted Files	Coverage Δ
neuralprophet/time_net.py	89.85% <77.77%> (ø)
neuralprophet/custom_loss_metrics.py	100.00% <100.00%> (ø)
neuralprophet/utils.py	82.58% <100.00%> (+1.50%)	⬆️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

[noxan]

LGTM - not sure if there are any other tensors for which we need to specify the device, yet anyhow better to have more of them on the right device 👍