lllyasviel / lllyasviel/ControlNet

How to validate the Controlnet?

Open
#745 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
34.1k
Forks
3k
PR merge metrics
No merged PRs in 30d

Description

Hi, I'm a code beginner. I've learned how to train a model, and I'd like to learn how to validate it and get a dynamic validation loss.

I tried adding check_val_every_n_epoch=1 inside trainer = pl.Trainer() in tutorial_train_sd21.py, but the output is still only the training loss.

Do I need to modify the file that creates the loss function to distinguish between the train_step and validation_step fields? How can I do this?
Thank you very much!

Contributor guide

No contributing guide indexed for this repository

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

Start with tutorial_train_sd21.py and the pl.Trainer setup, then inspect the loss-function code and the train_step and validation_step fields mentioned in the issue. Done means the training run reports a distinct validation loss rather than only the training loss.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.