How to train the self-data

huangmozhilv / u2net_torch

MICCAI2019:3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation

233 stars 53 forks source link

How to train the self-data #2

Closed yl255 closed 5 years ago

yl255 commented 5 years ago

Hi, Thank you for your great work! but I want to know how to train my self data with your model. For example, how to set the batch_size, and the patch_size and other parameters in the config.py. and how to inference the test data. Best, Yaliang

huangmozhilv commented 5 years ago

Hi @yl255, you can easily find the implementation details in the 2nd paragraph of "Preprocessing" section of the paper. More details can be found in paper of "nnU-Net".