Is "AssertionError: target _ has to be real" restriction necessary for RNN based models?

Open
#765 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
1-2 days
Newbie friendliness
45/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Stale
Tech stack
python, pytorch
Domain
machine-learning

Research direction

Start in pytorch_forecasting/models/rnn/init.py around the assertion near line 105 and trace how RecurrentNetwork.from_dataset() handles time_varying_unknown_reals. Read the related discussion in issue #433 for context. Done means an empty time_varying_unknown_reals list is accepted for RNN-based models without triggering the restriction.

Written by the indexing model from the issue text.

Description

Thank you for this amazing work. I think setting time_varying_unknown_reals=[] (as empty) should be possible for RNN based models (RecurrentNetwork.from_dataset()) too. The reasoning is similar to this issue #433. I noticed that there is a comment in the code to remove this assertion, maybe due to the similar intention. I was just wondering if that is just waiting for the implementation only.

Dominant language
Python
Stars
5k
Forks
912
Avg merge
3d 13h
Merged PRs (30d)
12

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from sktime/pytorch-forecasting

All issues in sktime/pytorch-forecasting

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.