8000 Run inference with model evaluation · Issue #2839 · MIC-DKFZ/nnUNet · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
Run inference with model evaluation #2839
Open
@Ixico

Description

@Ixico

Good morning,

I have a question. I have a trained nnUNet model and want to evaluate it on the test set. As I found, the only way to run inference is to specify OUTPUT_FOLDER, where all the predictions will be saved. Is there any option to run model evaluation on a test set? - I mean I have images and labels in imagesTs and labelsTs and I want DSC (preferrably before and after postprocessing).

If there is no ready tool for that, what would be the easiest way to do so? It sounds like pretty basic use case, so I'm probably missing something. If this question was already asked - sorry, I couldn't have found it.

Best regards!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0