dvlab-research/PFENet

Training Details

liushengnan1998 opened this issue · 1 comments

Hello,

It's a good job for FSS,and I am very interested in your work and tried to train myself.

But the test result of the trained model is a little lower than what you gave, so I would like to ask you about the details of the model training or what is the cause?

Thank you!

Thanks for your interest. Normally, this implementation may lead to slightly better performance than the results reported in our paper. You may find useful information in earlier issues where users also reported higher or lower performance that is caused by different training configurations and environments. Note that our implementation only supports 1 GPU training currently, and multiple GPUs will cause inferior performance.