Open synsin0 opened 2 years ago
Hi synsin0. For vovnet backbone, it is too large to fit in 3090. If you want to fit it in 3090, you can try:
torch.utils.checkpoint.checkpoint
, see https://pytorch.org/docs/stable/checkpoint.html?highlight=checkpointEnvironment: 4xRTX3090. Failure: train detr3d with resnet101 backbone dominates each card with 21GB memory. Train detr3d with vovnet backbone exceeds the memory limit. image_per_gpu is set to 1. I read from your paper that your experiment uses 8xRTX3090. How should I adjust for adaption of my training process?
Have you solved it?
Environment: 4xRTX3090. Failure: train detr3d with resnet101 backbone dominates each card with 21GB memory. Train detr3d with vovnet backbone exceeds the memory limit. image_per_gpu is set to 1. I read from your paper that your experiment uses 8xRTX3090. How should I adjust for adaption of my training process?