Neural-style: high resolution

[JeffCrusey]

my setup is crashing anything beyond about 600 pixels. id like to get as high of a resolution as possible. any tips for make something closer to 2k?

[xenon2]

buy more ram

[charlesfg]

A LOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOT more ram!

[janisozaur]

https://geizhals.eu/hp-lrdimm-64gb-m4z04aa-a1338532.html

[xenon2]

I tried to render 1920x1080 image and it takes about 50GB of RAM (using cpu backend).

[jcjohnson]

with cuDNN and Adam you should be able to fit 1920x1080 in 12GB of GPU
memory.

On Fri, Apr 1, 2016 at 2:41 PM, Jakub [email protected] wrote:

I tried to render 1920x1080 image and it takes about 50GB of RAM (using
cpu backend).

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub
https://github.com/jcjohnson/neural-style/issues/196#issuecomment-204575090

[charlesfg]

@jcjohnson do you think that is feasible to implement a trade off between time vs RAM. Using something like a memory map using SSD ?

[jcjohnson]

That is not easy to implement; it would also seriously degrade performance.
I've written more details in other issues.

On Fri, Apr 1, 2016 at 3:11 PM, Charles Ferreira Gonçalves <
[email protected]> wrote:

@jcjohnson https://github.com/jcjohnson do you think that is feasible
to implement a trade off between time vs RAM. Using something like a memory
map using SSD ?

—
You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
https://github.com/jcjohnson/neural-style/issues/196#issuecomment-204587771

[htoyryla]

Justin [email protected] kirjoitti 2.4.2016 kello 0.43:

with cuDNN and Adam you should be able to fit 1920x1080 in 12GB of GPU
memory.

Likewise, if one prefers L-BFGS, using nin-imagenet-conv instead of VGG19 produces 1920x1440 in 10GB (measured using CPU here).

Hannu

[hexus]

@htoyryla How long does that take for 1000 iterations? :grin:

[htoyryla]

Chris Andrew [email protected] kirjoitti 10.4.2016 kello 4.57:

@htoyryla How long does that take for 1000 iterations?

1 hour 40 minutes, on an i7 3.6 GHz 8 threads.

Hannu

[tommybananas]

Does increasing RAM help in gpu mode too or only cpu?

[jcjohnson]

More system memory will not help in GPU mode.

[0wnrepo]

It would be good to centralize these user reported benchmarks

[monik3r]

@htoyryla how do the results of nin-imagenet-conv look vs VGG19?

[htoyryla]

I find them useful enough. Difficult to compare when a) I cannot get images this large with VGG19 b) results with identical parameters on different models are not directly comparable.

Have a look here http://liipetti.net/erratic/tests/1920px-tests/

Since I made those tests, @ProGamerGov has reported that a lower tv_weight can produce sharper images with NIN (without adding too much noise that is). And I would not recommend using the highest conv layers with NIN, at least not without understanding what they contribute, see https://github.com/jcjohnson/neural-style/issues/226 .