Project-MONAI / Project-MONAI/tutorials

Training time of MAISI VAE

Open
#2,009 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 train the MAISI VAE from scratch using my dataset.
I wonder how long it takes to train on such a large dataset?

When I use 30k CT scans, it takes nearly 20 hours for 1 epoch on two A100. Is it correct? I use DDP, but I found it was even slower when I increased the GPU number.

If so, is there any method to accelerate the training process?

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 MAISI VAE training entry point and its DDP setup, then reproduce the reported 20-hour epoch on 30k CT scans using two A100 GPUs. No file or test is identified; done would require establishing whether the timing and scaling are expected and documenting a supported acceleration approach.

Written by the indexing model from the issue text.

Assessment

Tech stack
pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.