DA-TransUNet: Combining Dual Attention of Position and Channel with Transformer U-net for Medical Image Segmentation
GNU General Public License v3.0
120
stars
10
forks
source link
Error occurred during multi-GPU model training #4
Open
yangyin2016 opened 10 months ago
Thanks for your great work, I failed to use DDP to train the model, can you help me
RuntimeError: output with shape [0, 4, 1, 1] doesn't match the broadcast shape [0, 4, 1, 0]