Project-MONAI / Project-MONAI/MONAI

support of parallel inference in the EnsembleEvaluator

Open
#795 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Contribution wanted Feature request WG: Evaluation
Dominant language
Python
Stars
8.7k
Forks
1.6k
Avg merge
5d 1h
Merged PRs (30d)
20

Description

Is your feature request related to a problem? Please describe.
The EnsembleEvaluator sequentially runs inferences with different models.
Since these inferences are independent, would be great to support running them in parallel.

Describe the solution you'd like
may need to refactor the EnsembleEvaluator

Additional context
https://github.com/Project-MONAI/MONAI/blob/3a8fe35f7801d661b5e4d62269b1571524e13a0f/monai/engines/evaluator.py#L176

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 monai/engines/evaluator.py at line 176 and trace how EnsembleEvaluator runs each model inference. Define how independent inferences should execute in parallel and what behavior must remain unchanged; the issue is done when ensemble inference supports parallel execution without altering results.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.