NIH | National Cancer Institute | NCI Wiki  

Error rendering macro 'rw-search'

null

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 16 Next »

This page is a work in progress.

The Performing Predictions and Evaluating Models page describes how to generate predictions from a model asset collection (and optionally evaluate the model).

  • When generating predictions from an MT-CNN model, you can select a GDC manifest file (TXT) or a pathology report (TXT or PDF).
  • Optional: If you want to evaluate the model, MoDaC accepts CSV files for that purpose. Make sure the number of rows of data in the file for evaluating the model matches the number of rows of data in the file for generating predictions. 

The following attachments provide examples:

For more information on the GDC manifest file format, refer to the following page:

https://docs.gdc.cancer.gov/Encyclopedia/pages/Manifest_File/

  • No labels