search

Jianf-Wang / GBDL

A Pytorch implementation of CVPR 2022 paper "Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation"
54 stars 8 forks source link

Segmentation and uncertainty masks on test set #5

Open rohanbanerjee opened 1 year ago

rohanbanerjee commented 1 year ago

The README does not provide the scripts regarding how to get the binary segmentation masks and the uncertainty masks of the test set. What would you say would be the best way to get them? Many thanks!

Jianf-Wang commented 1 year ago

Hi. The codes for saving segmentation results and uncertainty maps are not included in the released version. You can modify the 'test.py' by yourself. For segmentation results, you can save 'output' in line 162 as images. For uncertainty map, you can calculate pixel-wise entropy by using 'out_seg' in line 162.