Fix issues

[JLrumberger]

What is the purpose of this PR?

This PR closes issues #13 , #12 , #10 and makes the inference pipeline more robust.

How did you implement your changes

1. Added the url to the cuda-compiled version of pytorch to the pyproject.toml to address Cuda not compiled #12
2. Changed the test-time augmentation loop in utils.py to address Inference fails for non-square images #13.
3. Hopefully, I addressed NaNs in predictions #14 by changing how the normalization is calculated. My guess is that for some FoVs, it might be possible to have no foreground, we get a NaN in the normalization value dict. I excluded nan from normalization value calculation that eventually fixes this.
4. I added some .DS_Store files to the data generation in the tests and added a sentence and a LOC to the inference notebook that says users should sort them out to address DS_Store and Mantis files included in cell table generation #10.
5. Switched macos CI backend from latest to 13, because it threw errors before because MPS (i.e. the apple silicon GPU) is not available on the CI.

Remaining issues
Probably #14 is not fixed by this, so it's left open.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[JLrumberger]

@ngreenwald merge without review, because of vacation.