ajhamdi / MVTN

pytorch implementation of the ICCV'21 paper "MVTN: Multi-View Transformation Network for 3D Shape Recognition"
98 stars 9 forks source link

I want to know the computing platform you use #11

Closed NotUr77 closed 2 years ago

NotUr77 commented 2 years ago

My computing platform is Nvidia GTX1080Ti. When I run the program, making the batchsize equal to 20, My CUDA memory will overflow.

ajhamdi commented 2 years ago

I use NVIDA V100 for the main experiments, but you can use GTX1080 as well (you have to reduce batch size )