search

graspnet / anygrasp_sdk

223 stars 22 forks source link

RuntimeError: CUDA out of memory. #3

Closed manish-kumar-01 closed 1 year ago

manish-kumar-01 commented 1 year ago

RuntimeError: CUDA out of memory. Tried to allocate 528.00 MiB (GPU 0; 1.95 GiB total capacity; 895.74 MiB already allocated; 385.38 MiB free; 990.00 MiB reserved in total by PyTorch)

I tried running sh demo.sh in grasp_detection with NVIDIA Quadro P600 ( 2GB ) Cuda is getting out of memory.

Is there any alternative, or what is the ideal GPU for this (minimum requirement)?

chenxi-wang commented 1 year ago

In most cases 2.5GB is OK. You can try running the program with GPU memory > 3GB.