Giters

Atcold / pytorch-CortexNet

PyTorch implementation of the CortexNet predictive model

Home Page:http://tinyurl.com/CortexNet/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

about the required memory size of GPU and training time

amiltonwong opened this issue · comments

commented

Hi, @Atcold ,

Thanks for releasing such a great package and I'm very interested in this work and want to have a practice on it. Could you reply the required memory size of GPU (I only have 980Ti , 6GB) to run the training process? Also could you elaborate on how long you trained your network in each settings (unsupervised and supervised) and which GPUs you used?

Thanks!

commented

6GB are enough for the models I am proposing in the paper.
Training time was around 40 minutes per epoch, and I've trained the network up to 30 epochs, so for at most 20 hours per experiment.
My 6 GPUs are GeForce GTX TITAN X, and they fit nicely two models each (they have 12GB of RAM), so I was running 12 experiments every night.

Please, let me know if you need any other detail.