Page 3 of 5

Re: Hardware best practices

Posted: Fri Dec 04, 2020 5:16 pm
by bryanlyon

I'd switch to the 2060. With the ability to turn on Mixed Precision you'll get huge speed increases and use less ram so you might even get a larger BS overall.


Re: Hardware best practices

Posted: Fri Dec 11, 2020 3:57 pm
by stepping-raz0r

Could you give an example of a hardware specs combo in the $2K (+/- $500) price range for someone just starting out?

(Based solely on faceswap considerations...)


Re: Hardware best practices

Posted: Fri Dec 11, 2020 8:18 pm
by bryanlyon

I'm not going to give specific advice since right now supply is difficult and sales/availability/driver support are in constant flux. Instead I'll just say buy the best hardware you can with a particular focus on the GPU. Faceswap can do multiple GPUs even if SLI/NVLink isn't supported. Others have posted requests for info on specific builds and you're likely to get a better response if you request help on a build instead of asking for us to design one for you.


Re: Hardware best practices

Posted: Fri Dec 11, 2020 10:42 pm
by abigflea
stepping-raz0r wrote: Fri Dec 11, 2020 3:57 pm

Could you give an example...
(Based solely on faceswap considerations...)

Will say Nvidia whatever you do.
30x0 series isn't working quite yet. Nvidia drivers and some other software are not updated to support FS(among other things), but may in a couple months.


Re: Hardware best practices

Posted: Tue Dec 15, 2020 2:09 am
by stepping-raz0r

Thanks, I realize there are far too many variables. Sorry, total noob: it's just that I'm looking for something I can unbox and plug in. Would the below nicely get the job done?

AMD Ryzen 7 3800X 3.9GHz 8-Core, B450 MATX, GeForce RTX 2080 Ti 11GB, 16GB DDR4, 960GB SSD


Re: Hardware best practices

Posted: Tue Dec 15, 2020 2:10 am
by bryanlyon

That'd be fine, and be quite usable for other uses like gaming. If you can wait for availability (and support) a 3080 might be a good choice instead of the 2080 ti.


Re: Hardware best practices

Posted: Thu Jan 07, 2021 3:36 pm
by abigflea
JohnnyMacIII wrote: Thu Feb 27, 2020 4:36 am

Thanks for the write up. How much RAM would you recommend? How much of a performance upgrade would it be from a 3700 to a 3900 if running two rtx 2070 supers? Thanks!

John

I think 16Gb would be fine, but I have 32 GB myself.
FaceSwap doesn't require much, but peripheral software like video editors, encoders, and whatnot tend to come into play with doing swaps and they do eat memory.

For your 2x 2070 I would highly suggest that you use Linux for the benefit. Xubuntu, or Ubuntu would be fine.

Additional considerations for your hardware is a good mainboard. Be 100% sure that the 2 slots used for your cards will both run at PCIe 8x for both. If you are really serious, get one that supports x16 for both, but those are costly. Investigate those well.
The GPU do need to speak to each other, and anything less than 8X, you'll lose performance.

My 2x 2070 go about 80% faster than a single.


Re: Hardware best practices

Posted: Thu Jan 14, 2021 2:12 pm
by RavingEnd

Hi, I'm not sure if this is the correct thread, but this is hardware related.
I see people in other threads getting 300 EG/s and the like with a 2070 and whatnot.
Using a GTX1060 6GB with Realface seems to net an average of 35EG/s.
Obviously I'm not expecting anything close to 2070 speeds, but is 35EG/s normal for a 1060?


Re: Hardware best practices

Posted: Thu Jan 14, 2021 3:55 pm
by bryanlyon
RavingEnd wrote: Thu Jan 14, 2021 2:12 pm

Hi, I'm not sure if this is the correct thread, but this is hardware related.
I see people in other threads getting 300 EG/s and the like with a 2070 and whatnot.
Using a GTX1060 6GB with Realface seems to net an average of 35EG/s.
Obviously I'm not expecting anything close to 2070 speeds, but is 35EG/s normal for a 1060?

Yes, this is normal. It really depends on the model as different models have different amount of computation to be done. Original on a 2070 can't be compared to Realface on a 1060. You're changing too many variables simultaneously.


Re: Hardware best practices

Posted: Thu Jan 14, 2021 4:45 pm
by RavingEnd
bryanlyon wrote: Thu Jan 14, 2021 3:55 pm
RavingEnd wrote: Thu Jan 14, 2021 2:12 pm

Hi, I'm not sure if this is the correct thread, but this is hardware related.
I see people in other threads getting 300 EG/s and the like with a 2070 and whatnot.
Using a GTX1060 6GB with Realface seems to net an average of 35EG/s.
Obviously I'm not expecting anything close to 2070 speeds, but is 35EG/s normal for a 1060?

Yes, this is normal. It really depends on the model as different models have different amount of computation to be done. Original on a 2070 can't be compared to Realface on a 1060. You're changing too many variables simultaneously.

Many thanks, so it's basically down to playing around with the different models and picking a good balance between speed and desired quality outcome.


Re: Hardware best practices

Posted: Thu Jan 14, 2021 5:36 pm
by tokafondo

Ok, so RTX Titan, the recommended not to buy card, has 24GB of RAM and 576 tensor cores.

What can be done with it? I mean... Is there actually a benefit of thas monster specs? Can some one train 1024x1024 there with batch sizes of 128? And I'm just putting high numbers there as an exaggeration.

On the practical side, the question would be: If I buy not one but two of these cards, and train 256x256 with batch sizes of 32... Would I get a zillion EG/s and train in 48 hours, what others do train in ten days?

Please help me understand. Thanks.


Re: Hardware best practices

Posted: Fri Jan 15, 2021 5:26 pm
by bryanlyon

RTX Titan has no real advantages over a 2080 ti which shares a nearly identical chip. It also barely has an advantage against a 2060 ti. Thats why it's not a recommended card.

If you buy 2 of them you'll get training about 2x a 2060 ti at 10x the price. If you really want that much power, just buy 2x 2060 tis which ALSO get nearly 2x a single 2060 ti.


Re: Hardware best practices

Posted: Mon Feb 08, 2021 9:05 pm
by cosmico
abigflea wrote: Fri Dec 11, 2020 10:42 pm

Will say Nvidia whatever you do.
30x0 series isn't working quite yet. Nvidia drivers and some other software are not updated to support FS(among other things), but may in a couple months.

Wow, did not know this. My friend was planning on updating his computer and was thinking about getting a rtx 30X0 series. Has there been any updates on if rtx 30X0 series are working yet?


Re: Hardware best practices

Posted: Tue Feb 09, 2021 10:21 am
by torzdf

Best CPU, Ram And GPU?

Posted: Fri Jun 04, 2021 5:20 pm
by californiaroll

Are more than 4 CPU Cores used effectively? Is an 8 core utilized enough to justify it? What about a 16 core?

How much Ram is optimal, 16GB, 32GB, more?

Is the amount of VRAM on a GPU the most important aspect? I was thinking about getting a NVIDIA 3060 12GB version. Are there better options for the money?

Thanks much, and sorry for all the questions.

I did try to google the recommended specs but my google fu failed me.


Re: Best CPU, Ram And GPU?

Posted: Fri Jun 04, 2021 5:35 pm
by bryanlyon
californiaroll wrote: Fri Jun 04, 2021 5:20 pm

Are more than 4 CPU Cores used effectively? Is an 8 core utilized enough to justify it? What about a 16 core?

How much Ram is optimal, 16GB, 32GB, more?

Is the amount of VRAM on a GPU the most important aspect? I was thinking about getting a NVIDIA 3060 12GB version. Are there better options for the money?

Thanks much, and sorry for all the questions.

I did try to google the recommended specs but my google fu failed me.

FaceSwap will use all the cores it can, but will run fine on a modern 4 core/8 thread CPU. I wouldn't recommend an 8 core JUST for FS, but if you have other uses, or if the price is similar then sure, get an 8 core.

System RAM needs are actually quite low. 8gb is enough but more can smooth things out. 32 is not necessary for FS.

VRAM is important on a card, but more than just amount is the speed of the vram. While a 3060 has 12gb, it's quite slow. Also having too much ram for the GPU's chip to properly utilize. If all you care about is the biggest model and not the time to train, the 3060 is the RAM leader, but you'll get better results from a more balanced card such as th 3060 ti which has significantly more speed, and is a better balanced card even with the reduced ram.


Re: Hardware best practices

Posted: Fri Jun 04, 2021 5:47 pm
by californiaroll

Thank you sir, you are a gentleman and a scholar.

Is there a better value card than the 3060 ti?

I don't mind spending more if it would be worth it to do so.

Thanks again.


Re: Hardware best practices

Posted: Fri Jun 04, 2021 5:55 pm
by bryanlyon
californiaroll wrote: Fri Jun 04, 2021 5:47 pm

Thank you sir, you are a gentleman and a scholar.

Is there a better value card than the 3060 ti?

Right now desktop GPUs are all but impossible to get ahold of. Honestly, whichever one you can get is probably going to be the one you want ;).

I'd suggest checkout out Cloud options or if those aren't acceptable a laptop for now. Best Buy has my recommended laptop: https://www.bestbuy.com/site/asus-rog-z ... Id=6452913 I have the 2060 version of this laptop and really like it and when you consider the difficulty in getting Desktop cards it's probably the best way to get GPU hardware right now.


Re: Hardware best practices

Posted: Fri Jun 04, 2021 7:09 pm
by californiaroll

I can get desktop cards double MSRP on eBay, which looks like what I will have to do.

If I am wanting the best quality video results I can get does that limit me to a 3090 with 24GB of VRAM?

Would it be more finically advantageous to rent a cloud based solution for this project, it's for a 2 minute video.


RTX 3060

Posted: Thu Oct 28, 2021 3:45 pm
by stowaway

I'm not having any luck with my Raedon (Asrock Radeon RX 6700 XT Challenger Pro 12G OC)

So I've decided I'm going to purchase a new video card.

Is the RTX 3060 chipset have fully compatiable?

Or can you suggest the best (mid range) card that can be purchased new (29/10/2021)