CUDA_ERROR_OUT_OF_MEMORY

sshaoshuai / PointRCNN

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

MIT License

1.72k stars 425 forks source link

CUDA_ERROR_OUT_OF_MEMORY #47

Open zhusuguanzhu opened 5 years ago

zhusuguanzhu commented 5 years ago

When i run the following command to evaluate the pretrained model python eval_rcnn.py --cfg_file cfgs/default.yaml --ckpt PointRCNN.pth --batch_size 1 --eval_mode rcnn --set RPN.LOC_XZ_FINE False . The Eroror: Call to cuDevicePrimaryCtxRetain results in CUDA_ERROR_OUT_OF_MEMORY Can you help me?

CarlSchwedes commented 5 years ago

It simply looks like that you even don't have enough memory to load one single batch. :) Are you running other gpu processes simultaneously to the PointRCNN? Could you provide the console output of nvidia-smi command?