Project-MONAI / Project-MONAI/tutorials

Blurry Results After Training and Poor Performance After Fine-Tuning on BTCV Dataset

Open
#2,052 2 comments 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

Hello,
I am currently trying to train and fine-tune your model. I am training the diffusion model using only the BTCV dataset. However, even after training for 20,000 iterations, the generated results are still quite blurry.

I also tried fine-tuning your pretrained diffusion model weights on the BTCV dataset, but after fine-tuning, the generation quality seems to degrade significantly and the results are not very good.

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 by reproducing the diffusion-model training and pretrained-weight fine-tuning runs described for the BTCV dataset, recording the configuration and results at 20,000 iterations. Compare generated outputs before and after fine-tuning, then identify whether the degradation is reproducible and document the setup and expected quality.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, pytorch
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.