Closed huan-zi closed 3 years ago
I suggest you use big patch, something like 144x144x16. It is relatively harder to train the model using small 3d patch.
Also, I strongly suggest you use another copy of my code: https://github.com/ginobilinie/medSynthesisV1
I 'm trying to generate CT from MRI with 3D vision, but the result doesn't look like CT. It's like a label map,no details.And the loss is already changing a little.Have you met this problem?