How to change the batch_size of DETR3D when training? about detr3d HOT 4 CLOSED

Here: https://github.com/WangYueFt/detr3d/blob/main/projects/configs/detr3d/detr3d_res101_gridmask.py#L188

But you might encounter a cuda out of memory if you are not using GPU with large enough memory

from detr3d.

Thank you for your answering, how large memory do we need per GPU for DETR3D? I see that you trained with 8 GTX3090 in your paper.

from detr3d.

I think I need to add a little detail, the samples_per_gpu denotes the batch size per gpu. And samples_per_gpu =1 means on each GPU there is one frame, which has 6 images(Each frame 6 camera).

Hi,
I think for ResNet-101 with FPN. samples_per_gpu takes around 20GB memory.

from detr3d.

Thx for your kindly response.

from detr3d.