HenriquesLab / HenriquesLab/ZeroCostDL4Mic

DEEPSTORM GOOGLE COLAB - issue with training the model

Open
#342 0 comments 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

When going to train the DEEPSTORM (2D) model, I am running into issues with the system RAM usage and the coding. It tells me the file save format cannot be hdf5 and must be in keras format. After I change the code from hdf5 to keras there is either an issue with the training taking up too much system RAM or there is another issue with the code.

To Reproduce
Steps to reproduce the behavior:

  1. Go to 4.4. Start Training
  2. Click on run cell
  3. See error

Expected behavior
I expect the cell to run without any errors and to get a trained model.

Screenshots

Image

Desktop (please complete the following information):

  • OS: MacOS Sequoia 15.2
  • Browser Safari
  • Version 18.2

Add any other context about the problem here.

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

Start at the DEEPSTORM (2D) notebook's “4.4. Start Training” cell and reproduce the failure in Google Colab, recording the exact error and RAM behavior. Done means the cell runs without the reported save-format or memory failure and produces a trained model.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook
Domain
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.