30.03.2016-13:24:44 :: Something smarter than us is going to emerge


node:	30.03.2016-13:24:44
template:	4
parent:	deep dreamz are made of silk
owner:	drakh
viewed by:
created:	30.03.2016 - 13:24:44

cwbe coordinatez:
101
63529
7956078
8122517

ABSOLUT
KYBERIA

permissions
you:	r,
system:	public
net:	yes

fajn resources
http://handong1587.github.io/deep_learning/2015/10/09/dl-and-arts.html

0000010100063529079560780812251708122528

https://github.com/DmitryUlyanov/fast-neural-doodle

000001010006352907956078081225170812252808122537

nevies inak ako dlho to asi pocita takyto jeden doodle?

00000101000635290795607808122517081225280812253708127833

do roka a do dna budu realtimove

0000010100063529079560780812251708122528081225370812783308127836

len kolko to bude stat ;)

Tesla P100 ma celkom killer specifikacie
http://arstechnica.com/gadgets/2016/04/nvidia-tesla-p100-pascal-details/

len cena tejto srandy je zabavna :) http://www.nvidia.com/object/deep-learning-system.html

aunching alongside the Tesla P100 is Nvidia's DGX-1 Deep Learning System. The DGX-1 features eight Tesla GP100 GPU cards providing 170 teraflops of half-precision performance from its 28,672 CUDA cores. The DGX-100 also features two 16-core Intel Xeon E5-2698 v3 2.3GHz CPUs, 512GB of DDR4 RAM, 4x 1.92TB SSD RAID, dual 10GbE, 4x InfiniBand EDR network ports, and requires a maximum of 3200W of power. It'll cost a mere $129,000 (~£103,000) when it launches in June.

000001010006352907956078081225170812252808122537081278330812783608134942

http://www.creativeai.net/posts/Yyxu837ecBsa4PBiZ/precomputed-real-time-texture-synthesis-with-generative

000001010006352907956078081225170812252808122537081278330812783608127846

Toto je praveze nieco ako faceswap, bude z toho mobilna appka skor alebo neskor. Limitovana, pravdaze, ale bude :)

aha, 'three orders of magnitude faster': https://twitter.com/_mayfa/status/718079116705005569

00000101000635290795607808122517081225280812253708122538

lenivy klikat co ;)

Multiscale

Processing the image at low resolution first can provide a significant speed-up. You can pass a list of resolutions to use when processing. Passing 256 means that the images and masks should be resized to 256x256 resolution. With 0 passed no resizing is done. Here is an example for cmd parameters:

-num_iterations 450,100 -resolutions 256,0 Which means: work for 450 iterations at 256x256 resolution and 100 iterations at original.
Monet and Renoir examples take ~1.5 min to process with these options.

0000010100063529079560780812251708122528081225370812253808122545

fuh sorry, ale dik
interesantne