search

rbgirshick / py-faster-rcnn

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
Other
8.11k stars 4.11k forks source link

memory required during test #6

Open kaishijeng opened 8 years ago

kaishijeng commented 8 years ago

I have NVidia 960 GPU card with 4 GB RAM and tools/demo.py complains insufficient memory with VGG16 model. ZF model is running OK. Is there a way to reduce GPU memory usage with VGG16 model?

Thanks, Kaishi

ericromanenghi commented 8 years ago

I don't know if you still need help, but I have a similar problem, and I fixed using CUDNN.

If you could solve your problem, please close the issue.

atinesh-s commented 5 years ago

I don't know if you still need help, but I have a similar problem, and I fixed using CUDNN.

If you could solve your problem, please close the issue.

Hello ericromanenghi, Could you please tell how you solved the problem with CuDnn I am facing the same issue.