Project-MONAI / Project-MONAI/tutorials

Dice Loss is Negative for some steps

Open
#1,434 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
2.5k
Forks
803
Avg merge
6d 22h
Merged PRs (30d)
3

Description

Hi,

I am trying to follow the 3D segmentation Tutorial,

When I run the code on CPU local machine, the tutorial is working fine,
But the moment I start training on GPU cluster (CUDA), the model performance is poor and it give dice loss negative for some trainining steps

Contributor guide

Open the contributing guide

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 with the 3D segmentation Tutorial and compare its CPU and CUDA training paths. Reproduce the negative Dice loss on the GPU cluster, then identify and document the CUDA-specific cause and verify that training produces valid loss values and expected model performance.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, pytorch
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.