Fixed bug where trying to run model prediction on single timepoint where start = 0 and stop = 0 would evaluate whole timelapse

[SergeEParent]

What does this PR do?

• This PR fixes a bug where, when a CytoDLModel was asked to predict on a single timepoint where T start = 0 and T end = 0, then it would instead evaluate a range including all timepoints.
• Specifically, I was trying to pass a list of coordinates at a specific timepoint to CytoDL to evaluate through a config file and when start and stop were both 0 the whole timelapse would be evaluated (unexpected), but when any other timepoint was chosen only a single timepoint was evaluated (expected).
• There are no new dependencies required for this change.
• I don't think that this change introduces any breaking changes.
• I tried to run pytest locally but it stopped making progress 56% and after 1.5 hours at I gave up (but it passed everything up to that point)
• I ran the pre-commit hooks and they all passed except that nbstripout was skipped because "no files to check"

Before submitting

• Did you make sure title is self-explanatory and the description concisely explains the PR?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you list all the breaking changes introduced by this pull request?
• Did you test your PR locally with pytest command?
• Did you run pre-commit hooks with pre-commit run -a command?

Did you have fun?

Yes.