Philip-Bachman / amdim-public

Public repo for Augmented Multiscale Deep InfoMax representation learning
MIT License
397 stars 60 forks source link

training self sueprvised learning on multi-gpu #16

Open bhat-prashant opened 3 years ago

bhat-prashant commented 3 years ago

Hi, I am really new to self supervised learning. I would like to know how do you adjust no.of epochs when you train on multi-gpu.

I am intending to train on ImageNet. Unfortunately, I cannot fit mini-batch of 256 in one gpu. As for as I understand, when I train on 4-gpu, even if I train for 100 epochs, the no.of epochs trained will be effectively 100/4=25 as number of gradient updates will also be divided by 4. Please correct me if I am wrong.

Please let me know how have you accounted for that in your implementation.

Thanks