search

xmengli / H-DenseUNet

TMI 2018. H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
526 stars 161 forks source link

slow training #29

Closed leetesua closed 5 years ago

leetesua commented 5 years ago

When i run train_2ddense.py, every epoch takes more than 1000s. I use 2 GPUs so I changed the '-b' paramaters to be 20 instead of 40. And Considering the total epoch is set to be 6000, the whole training process could take months.

Is that normal? How could I speeeeed up? Thanks in advance!

xmengli commented 5 years ago

The model would converge before 6000 epoch. I forgot the exact epoch. Normally, it takes 2-3days using 4 GPUs.