Open robert-fuess opened 6 years ago
Basically you divide the model sequentially onto your different GPUs. So you should be able to increase the image size with a second GPU even if it doesn't have the same amount of memory as the first GPU.
https://github.com/jcjohnson/neural-style/issues/428#issuecomment-338367106
No you cant. You could emulate but is a different process not the same.
On Sun, Feb 18, 2018 at 10:31 PM, ProGamerGov notifications@github.com wrote:
Basically you divide the model sequentially onto your different GPUs.
428 (comment)
https://github.com/jcjohnson/neural-style/issues/428#issuecomment-338367106
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/jcjohnson/neural-style/issues/449#issuecomment-366599635, or mute the thread https://github.com/notifications/unsubscribe-auth/AhbMugDpvGtQubzwtzwXn0H7A1V1lHghks5tWRUtgaJpZM4SHGxz .
Hello, just a short question: I have a GeForce GTX 1070 with 8GB of memory and i'm able to produce pictures with 840px. If i add another graphic card doubles the the memory to 16GB so i could produce images in higher resolution or doesn't work graphic memory like that?
Thx