HenriquesLab / HenriquesLab/ZeroCostDL4Mic

Error: StarDist_2D keeps disconnecting runtime in the middle of the run

Open
#166 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
652
Forks
144
PR merge metrics
No merged PRs in 30d

Description

I am using StarDist_2D to quantify lysosomes from my STORM images using my own training data. The run time is 4-6h. However, the training almost never goes to the end; instead the connection is disconnected somewhere in the middle and even if I could reconnect, the training does not start where it was left. So I need to start from the beginning. Often I get a message that I have reached the user limit even though in the manual it says that max run length is 12h (and my runs are max 6h). I have restarted the same run for tens of times. With this error it seems impossible to screen different training parameters since it is not possible to finish even one run. I'd really appreciate your help with this matter! Thanks a lot!!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file or test is named in the report. Begin by reproducing a long StarDist_2D training run in the Google Colab notebook and checking when the runtime disconnects or reports the user limit; done means identifying a reliable cause and confirming that a run can complete or resume without restarting.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
Domain
cloud, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.