rixez

Hello @JuanDuranMcgill, I appreciate your interest in this repo. About the changes that you'd like to implement, you can do that by making a new trainer function with the SwinUNETR...

Hello @tangqishi, This repo used nnunetv1.

Hi @TueNguyen2006, Thank you for informing me about the link. I have reuploaded the models and updated the link. Please try to download it again. Thanks!

Hi @dominikaxx, I assume you are talking about the `emb_shape` parameter. This parameter specifies the shape of the feature maps to calculate the embedding parameters for axial attention. Since Unet...

The number of heads and dim_heads is increased according to the formula to improve the model capacity. Since these two numbers are specified starting at the highest resolution feature maps,...

Hi @DanielNajarian, 1. You can run this repo as a standalone. This repo contained all functionalities of the original nnUNet repo. 2. You should first convert your data to the...

Please run this command at the root folder to install the repo as a library: `pip install -e .`