Semantic-Aware-Attention-Based-Deep-Object-Co-segmentation icon indicating copy to clipboard operation
Semantic-Aware-Attention-Based-Deep-Object-Co-segmentation copied to clipboard

Published 20 hours ago • verified publisher icon sairin1202

Training is very slow

Open sidgairo18 opened this issue 5 years ago • 2 comments

The training is very slow. Even the evaluate part takes hours to finish.

How much time did it take to train the model?

sidgairo18 avatar Jul 25 '19 04:07 sidgairo18

To accelerate training step, you can fix the parameters in the backbone model or input the features instead of the images. If you have two or more GPUs, you can finish training the model within one day.

sairin1202 avatar Jul 26 '19 06:07 sairin1202

Thank you for your reply. I am currently using a Batch-Size of 20 with 4 GPUs and training the model end to end.

I have 500K pairs for training. It takes 1 day for a single epoch with batch size 20.

sidgairo18 avatar Jul 27 '19 06:07 sidgairo18