Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Hardcore weight txt path #1089

Merged
merged 3 commits into from
Oct 24, 2024
Merged

Conversation

vloncar
Copy link
Contributor

@vloncar vloncar commented Oct 23, 2024

Description

Currently, weight loading requires running from the specific directory so the relative paths match. In addition, predict() expects all backbends to have a format of <output_dir>/firmware which may not be the case forever in the future (one API in particular will have a different hierarchy). With this PR we ensure the created .so file is has the weights for in absolute path, so loading it from any directory will work, and predict no longer has to change folders.

Type of change

  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)

Tests

No need for new tests, all tests will fail if it doesn't work.

Checklist

  • I have read the guidelines for contributing.
  • I have commented my code, particularly in hard-to-understand areas.
  • I have made corresponding changes to the documentation.
  • My changes generate no new warnings.
  • I have installed and run pre-commit on the files I edited or added.
  • I have added tests that prove my fix is effective or that my feature works.

@JanFSchulte JanFSchulte merged commit 39d0e91 into fastmachinelearning:main Oct 24, 2024
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants