search

nabsabraham / focal-tversky-unet

This repo contains the code for our paper "A novel focal Tversky loss function and improved Attention U-Net for lesion segmentation" accepted at IEEE ISBI 2019.
357 stars 72 forks source link

Is upsample_g an upsampled version of g? #2

Closed phernst closed 5 years ago

phernst commented 5 years ago

From newmodels.AttnGatingBlock: https://github.com/nabsabraham/focal-tversky-unet/blob/2c6ad9535bf6d1bc73371b0f6a57f7daf0af458e/newmodels.py#L86-L93

So upsample_g is also half the (spatial) size of x and there is no need to calculate the strides in Conv2DTranspose since it will always be 1, or am I missing something?

The 2x UP step on x_l in Fig. 3 of your paper should be 2x DOWN then, right?

nabsabraham commented 5 years ago

hi @phernst! sorry about the super late reply! yes you are correct, the diagram is wrong but the code is correct. I will update this repo soon :)