Cross validation may be better

JohnleeHIT / Brats2019

[BrainLes2019] Multi-step cascaded network for brain tumor segmentations (tensorflow)

https://arxiv.org/abs/1908.05887

MIT License

95 stars 24 forks source link

Cross validation may be better #9

Open yianzhongguo opened 4 years ago

yianzhongguo commented 4 years ago

Hi sir, your code is very good. It looks like that you use the first 50 patients in training data set to validate the outcome of the model after many epoch training. I think maybe cross validation can be used, do you agree, thank you very much!

JohnleeHIT commented 4 years ago

Yes, you are right, i did five fold cross validation when finnally submit the result.