search

CVMI-Lab / UHDM

(ECCV2022) This is the official PyTorch implementation of ECCV2022 paper: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
Apache License 2.0
207 stars 28 forks source link

training slow #28

Open qingyunwudaoletu opened 5 months ago

qingyunwudaoletu commented 5 months ago

I use one 3070ti, training with whole night, just complete one epoch. The training process seems very slow

XinYu-Andy commented 5 months ago

I use one 3070ti, training with whole night, just complete one epoch. The training process seems very slow

This is not an expected behavior. Please check if your program successfully uses the GPU.

qingyunwudaoletu commented 5 months ago

I use one 3070ti, training with whole night, just complete one epoch. The training process seems very slow

This is not an expected behavior. Please check if your program successfully uses the GPU.

Thankyou, i have only single GPU, the GPU_ID is wrong. Great wrok. Best wishes