I'm training a 3D U-Net on an EM dataset of a brain. The objective is to segment neurons in it. During the experiments, I've noticed, different random initialization of the network leads to different performances. I evaluate the performance based on mean Intersection over Union, and I observe differences as large as 5%.

I use xavier initilization with a uniform distribution and use a constant learning rate of 1e-4.

  • $\begingroup$ Just want to confirm, do you use early stopping? $\endgroup$ – itdxer Nov 15 '18 at 11:27
  • $\begingroup$ Yes, I'm using early stopping. I pick the model with the highest validation set accuracy and report its performance on the test set. $\endgroup$ – Optimus Nov 16 '18 at 10:24
  • $\begingroup$ what's the question? $\endgroup$ – shimao Nov 20 '18 at 21:51

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.