Bug Fix for #1071: NHiTs encoder/decoder covariate size difference bug

[bendavidsteel]

Description

Fix for #1071 and #1065

[jdb78]

Can we add a test? Looks like it makes a lot of sense but would like to have a test for this as it is an actual change in the model

[codecov-commenter]

Codecov Report

All modified lines are covered by tests ✅

Comparison is base (4384365) 90.11% compared to head (c4a8339) 90.19%.
Report is 17 commits behind head on master.

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #1359      +/-   ##
==========================================
+ Coverage   90.11%   90.19%   +0.08%     
==========================================
  Files          30       30              
  Lines        4714     4724      +10     
==========================================
+ Hits         4248     4261      +13     
+ Misses        466      463       -3     

Flag	Coverage Δ
cpu	90.19% <100.00%> (+0.08%)	⬆️
pytest	90.19% <100.00%> (+0.08%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files	Coverage Δ
pytorch_forecasting/models/base_model.py	88.11% <100.00%> (-0.08%)	⬇️
pytorch_forecasting/models/nhits/__init__.py	97.33% <100.00%> (+0.07%)	⬆️
pytorch_forecasting/models/nhits/sub_modules.py	83.95% <100.00%> (+0.30%)	⬆️

... and 1 file with indirect coverage changes

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[bendavidsteel]

Sure! Added a new test for NHiTs, confirmed it fails on master and passes on my branch

[jdb78]

Great PR! thanks a lot

[bendavidsteel]

Thanks! Just fixed the linter problem, looks like you'll need to approve again to get the workflows to run