NVIDIA / vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Other
8.6k stars 1.2k forks source link

Possible parameters tuning for smaller GPU memory usage #94

Open ligua opened 5 years ago

ligua commented 5 years ago

Hi

Sorry to disturb you.

I am wondering whether there are parameters that I can tune in order to reduce the size of the model. I only have 4 12GB GeForce GTX TITAN X available for training. So I am wondering what parameter can I tune to reduce the size of model.

PS: I am training on 256*256 images, so perhaps the number of filters in the generator can be smaller.