training/inference on laptop

Question

training/inference on laptop

amkurup opened this issue 4 years ago · 5 comments

Hi,
Is it possible to train or run inference on a single laptop (System76 - GeForce GTX 1650 - 4Gb)? Both these now return "Cuda out of memory error". nvidia-smi shows that most of the memory is free.

Is there a workaround for this or does it have to be done on a stronger system?

Answer 1 · 2021-01-10T12:33:23.000Z

Try to reduce the batch size as more as possible and see if you can run the training process. But in my opinion, this GPU is not enough due to the large size of pointcloud data.

Answer 2 · 2021-01-10T20:02:01.000Z

I have tried reducing the batch size and also tried to use only sequence 01 for training (as a test). Still the same issue.

Answer 3 · 2021-01-10T20:04:19.000Z

Are you using darknet53 as the backbone of your model? This one requires more memory, than squeezeseg e.g., so you could try a different backbone

Answer 4 · 2021-01-10T20:13:54.000Z

I am using darknet53. Thanks, will try out squeezeseg!

Answer 5 · 2021-01-13T06:21:37.000Z

squeezesegV2 works on this system. This will do for now!
Thanks