Erica

Error occurs when data's brain region size lower than patch size

1

Hi, when do gen_map on validation dataset, some datas occurs error like this:  I found the reason is data's brain region is lower than patch size:  My pacth...

Definition of all_stages_loss, how to choose suitable coefficient for separate stage loss?

2

Definition of all_stages_loss is: self.all_stages_loss = 0.4 * self.total_wght_loss + 0.8 * self.stage2_loss + self.stage3_loss, why use 0.4、0.8、1 as the three stage's loss coefficient?

You load pre-weights only for the first mode named unet,did you?

2

In your code file "oprations.py", you extract some layers for fine-tuning, and I found these layers only from the first mode unet. Does it means just do fine-tuning for unet...

Can you share your dataset?!

5

Sorry, I really hope you can share your dataset. Thank you very much!

the arguments' meaning

1

arguments ratio_gan2seg : trade-coefficient between GAN loss and segmentation loss discriminator : type of a discriminator (pixel or patch1 or patch2 or image) I really don't know how to put...