patrick-kidger / patrick-kidger/diffrax

how to define the vector_field

Open
#122 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Python
Stars
2.1k
Forks
189
Avg merge
3d 18h
Merged PRs (30d)
1

Description

Hi patrick,
First of all, Thanks for this excellent library!
I have observed 7000 time series data, for example,
0.00E+00
2.22E-01
3.33E-01
1.11E-01
8.89E-01
8.89E-01
1.11E-01
7.78E-01
2.22E-01
4.44E-01
1.00E+00
2.22E-01
8.89E-01
1.11E-01
1.11E-01
1.11E-01
4.44E-01
7.78E-01
8.89E-01

ready to use Latent ODE and Neural CDE, how to define the vector_field in the example?
how can I deal with it?
Thanks a lot.

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.

Research direction

Read the Latent ODE and Neural CDE example material linked from the Diffrax documentation, then compare it with the reported 7000-point time-series input. Done would require a project-specific explanation of how vector_field should be defined; the issue names no source file or test to update.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.