Training time and GPU

[Aristot1e]

I got a question about the training time is too long and the GPU memory is too high. I use GTX 3090 24G, but the batch size I can set just 1, if setting 2 I'll get cuda out of memory. So I wanna ask to how I can speed up my training time. About the GPU memory, whether the input image can be blocked and then entered to increase the batch size. Can you share some details about training? Thank you so much.

[KeWang0622]

High, thanks for your question! The training time is inherently long due to the large datasets and unrolled networks. In terms of GPU memory, in our paper, we used the batchsize of 1. To increase the batch size, I would recommend using average gradients, or GPU parrallization.