Follow-up tensors on wrong device

[karl-richter]

🔬 Background

As pointed out in #1002, some tensors have remained on the CPU when training with a GPU. This has previously been adressed #1010, it seems like some tensors remained on the wrong device.

🔮 Key changes

• Moved all tensors to the correct device (checked all usages of torch.zeros, torch.ones, torch.tensor via strg+F)
• Added the usage of self. meta_used_in_model in the forward function

📋 Review Checklist

• I have performed a self-review of my own code.
• I have commented my code, added docstrings and data types to function definitions.
• I have added pytests to check whether my feature / fix works.

Please make sure to follow our best practices in the Contributing guidelines.

[codecov-commenter]

Codecov Report

Merging #1023 (676eaa0) into main (e06945e) will increase coverage by 0.06%.
The diff coverage is 87.50%.

@@            Coverage Diff             @@
##             main    #1023      +/-   ##
==========================================
+ Coverage   90.20%   90.26%   +0.06%     
==========================================
  Files          21       21              
  Lines        4748     4737      -11     
==========================================
- Hits         4283     4276       -7     
+ Misses        465      461       -4     

Impacted Files	Coverage Δ
neuralprophet/time_net.py	90.57% <87.50%> (+0.55%)	⬆️

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

[github-actions]

676eaa0

Model Benchmark

Benchmark	Metric	main	current	diff
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	4.84	4.87	0.62%	✅
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	12.49	12.84	2.8%	✅
YosemiteTemps	MAE_val	1.72949	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	101.13	103.76	2.6%	✅

Model training plots

Model Training

PeytonManning

YosemiteTemps

AirPassengers

[alfonsogarciadecorral]

accelerator="cuda" working nicely on my GPU!

[alfonsogarciadecorral]

• I made a commit to add the meta is None condition at the beginning of the forward.

• np working on my gpu now