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

ERROR to load particles with Jupyter notebook during cryoDRGN filtering after a high-res train with --ind #363

Closed
MunozHernandez opened this issue Apr 16, 2024 · 2 comments
Assignees

Comments

@MunozHernandez
Copy link

Describe the bug
ERROR when loading particles with Jupyter notebook during cryoDRGN filtering after a high-res train with --ind

To Reproduce
Jupyter notebook worked well in a filtering job of previous triain (00_vae) but when I use the --ind selected.pkl particles for a second round training (01_vae) then I can not filter because an error during loading the particle in the Jupyter notebook of the cryodrgn.filtering.

Expected behavior
I expected the filtering index particles to be the same as load input particles.
Error appears:
Additional context
Please find below the Jupyter screenshoot with out put:
image


@michal-g
Copy link
Collaborator

Thanks for pointing out this issue! We believe the bug was isolated to the notebook itself (specifically the preceding call to dataset.ImageDataset should not include ind=ind_orig as the filtering is already done manually after), so the rest of your experiment output should be fine.

We will be pushing a release including a fix to this bug; in the meantime, you can try an early version of the patched notebooks using our new development release channel:
pip install -i https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ 'cryodrgn==3.3.0a1.dev4'

@michal-g
Copy link
Collaborator

FYI: we found another related issue with how the filtering was done in this notebook, and fixed it, as described at #374

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

No branches or pull requests

2 participants