search

zhyever / Monocular-Depth-Estimation-Toolbox

Monocular Depth Estimation Toolbox based on MMSegmentation.
Apache License 2.0
907 stars 104 forks source link

Bug during training #76

Open Jmh0527 opened 1 year ago

Jmh0527 commented 1 year ago

The data set I use is nyu depth v2. I encountered the same error with both depthformer（depthformer_swinl_22k_w7_nyu.py） and binsformer（binsformer_swinl_22k_w7_nyu.py）. My execution command is

python /home/data1/jmh/Depth_Estimation/Monocular-Depth-Estimation-Toolbox-main/tools/train.py /home/data1/jmh/Depth_Estimation/Monocular-Depth-Estimation-Toolbox-main/configs/binsformer/binsformer_swinl_22k_w7_nyu.py --gpu-ids 2

cuda:11.1 torch:1.8.0 torchvision:0.9.0 python:3.7.16

image

This error will appear when I use dual card training. Why does this happen?

zhyever commented 1 year ago

It could be sort of weird. I guess it is a Pytorch bug. Maybe you should try solutions on google.