search

mikevoets / jama16-retina-replication

JAMA 2016; 316(22) Replication Study
https://doi.org/10.1371/journal.pone.0217541
MIT License
110 stars 37 forks source link

.scale_normalize from lib/preprocess.py #15

Closed sdsawtelle closed 5 years ago

sdsawtelle commented 5 years ago

Thank you for the repo Mike.

I am following the README instructions to evaluate on a custom data set, but in the first step I do not find scale_normalize in the current version of lib/preprocess.py, but I do see it in the oldest version. Should we be using _resize_and_center_fundus_all instead?

Thanks!

mikevoets commented 5 years ago

You're welcome, Sonya! I'm glad you are interested in our project.

Yes, you're right. The README instructions to apply pre-processing on a custom data set seem to be outdated. I have updated these instructions now.

The method that has replaced scale_normalize is _resize_and_center_fundus_all indeed. But the proper method to use would be resize_and_center_fundus from lib.preprocess, which is used as a wrapper around _resize_and_center_fundus_all.

sdsawtelle commented 5 years ago

Much appreciated Mike!