Benchmarking

Talk about Hardware used for Deep Learning


Locked
User avatar
230V
Posts: 20
Joined: Sun Jan 19, 2020 6:20 pm
Answers: 1
Has thanked: 7 times
Been thanked: 2 times

Benchmarking

Post by 230V »

have no idea if this question ever be posted; but an simple benchmark to get an idea how well hardware setups are computing via faceswap would be nice.

a ranking chart would give users ideas how to archive better computing power.

User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Benchmarking

Post by bryanlyon »

The problem is it's SO subjective, it varies heavily on CPU, GPU, Model, PCI-E Lanes, and more. It's almost impossible to properly acccount for them in any meaningful way.

User avatar
230V
Posts: 20
Joined: Sun Jan 19, 2020 6:20 pm
Answers: 1
Has thanked: 7 times
Been thanked: 2 times

Re: Benchmarking

Post by 230V »

it would be enough to see in numbers how well or bad the setups compute. to compare the systems and determine what is possible to get better results out of my setup.

User avatar
torzdf
Posts: 2649
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 128 times
Been thanked: 622 times

Re: Benchmarking

Post by torzdf »

I have no issues with someone starting this kind of thread, with the caveats that [mention]bryanlyon[/mention] mentions.

My word is final

Locked