search

yhw-yhw / D2HC-RMVSNet

The official repository of the paper "Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking" (ECCV2020 Spotlight)
MIT License
109 stars 9 forks source link

Training stage memory consumption #12

Closed saedrna closed 3 years ago

saedrna commented 3 years ago

Hi,

I am doing training of D2HC-RMVSNet. I am using D=192, nviews=3 and batch=1, image_scale=0.25. I am using the BlendedMVS dataset for training on one RTX 3080 Ti (12GB mem). However, unfortunately, at d=160 of the regularization stage, I am running out of memory. I am not using apex for automatic mixed precision. My question is, in the training stage, will the recurrent structure will save memory? It seems it does not.

Thanks, Han

saedrna commented 3 years ago

Just found this is a duplicate of #8 .