Closed longmalongma closed 11 months ago
Does anyone else have this problem?
The training parameters are different so I would expect there to be some differences.
The training parameters are different so I would expect there to be some differences.
But now my training speed for DEVA is more than 10 times slower than training for XMem, is this normal? Is there any solution? I cannot reproduce DEVA at this speed.
The training speed depends on various factors. I think the general rule is that if your GPU has high utilization (and high power consumption), it is doing fine.
The training speed depends on various factors. I think the general rule is that if your GPU has high utilization (and high power consumption), it is doing fine.
My gpu usage is almost zero now, mainly because I am stuck in reading data for a long time,
Is it normal for DEVA's training speed to be much slower than XMem? I am training DEVA on the same machine and in the same environment, but the speed is very slow. I don't know why.