Skip to content

Comments

Feaure: Added Apple silicon support in nb finetuning.#1161

Merged
anwai98 merged 1 commit intocomputational-cell-analytics:devfrom
HendrikLamar:feature/apple_silicon_support_fintuning_nb
Feb 11, 2026
Merged

Feaure: Added Apple silicon support in nb finetuning.#1161
anwai98 merged 1 commit intocomputational-cell-analytics:devfrom
HendrikLamar:feature/apple_silicon_support_fintuning_nb

Conversation

@HendrikLamar
Copy link
Contributor

@HendrikLamar HendrikLamar commented Feb 11, 2026 •
edited
Loading

Checks if Cuda or MPS (Apple Silicon) is available. Otherwise defaults to CPU.

@HendrikLamar
Feaure: Added Apple silicon support in nb finetuning.
d4bf567 
Checks if Cuda or MPS (Apple Silicon) is available. Otherwise defaults to GPU.
@review-notebook-app
Copy link

review-notebook-app bot commented Feb 11, 2026

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

@anwai98
Copy link
Collaborator

anwai98 commented Feb 11, 2026

Hi @HendrikLamar,

Thanks for the PR. This definitely looks good (we missed it right from the very beginning actually hehe).

I'll go ahead and merge this once the tests pass!

PS. FYI, we have a function under micro_sam.util.get_device which could do the device mapping automatically. Now that you mention, I'll probably switch to it once I've merged this PR (in a different PR)!

@anwai98
Copy link
Collaborator

anwai98 commented Feb 11, 2026

The tests are broken because the dev and master are not completely aligned with the trackastra fixes we made recently. I merged master to dev and restarted the tests again! (in case they still fail for the tuple x node-related issue in multi dimensional segmentation, let's not worry too much about it and merge this)!

@anwai98
Copy link
Collaborator

anwai98 commented Feb 11, 2026

Things aren't upstream, that's why they are breaking rn. The PR doesn't cause this explicitly. Therefore, I'll go ahead and merge this. Thanks again @HendrikLamar for the PR!

@anwai98 anwai98 merged commit f463687 into computational-cell-analytics:dev Feb 11, 2026
0 of 12 checks passed
anwai98 added a commit that referenced this pull request Feb 11, 2026
@anwai98 @constantinpape @HendrikLamar
Merge dev to master (#1162)
a4a4eaf 
* Fix issue in batched inference

* Feaure: Added Apple silicon support in nb finetuning. (#1161)

Checks if Cuda or MPS (Apple Silicon) is available. Otherwise defaults to GPU.

* Simply device allocation in finetuning notebook (#1163)

* Simply device allocation in finetuning notebook

* Update finetuning python scripts

---------

Co-authored-by: Constantin Pape <constantin.pape@informatik.uni-goettingen.de>
Co-authored-by: Hendrik Windel <15370203+HendrikLamar@users.noreply.github.com>
@HendrikLamar HendrikLamar deleted the feature/apple_silicon_support_fintuning_nb branch February 11, 2026 19:03
anwai98 pushed a commit that referenced this pull request Feb 13, 2026
@HendrikLamar @anwai98
Feaure: Added Apple silicon support in nb finetuning. (#1161)
10a71e7 
Checks if Cuda or MPS (Apple Silicon) is available. Otherwise defaults to GPU.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@constantinpape constantinpape constantinpape approved these changes

@anwai98 anwai98 anwai98 approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@HendrikLamar @anwai98 @constantinpape