Hi,
I played 100 games against Stockfish 10 x64 1CPU under CEGT 40/20 conditions. Grafikcard is GTX 1650:
1 LCZero 0.23.1 Cuda (58573) +45 +23/=67/-10 56.50% 56.5/100
2 Stockfish 10.0 x64 1CPU -45 +10/=67/-23 43.50% 43.5/100
I ask me: are larger networks really better under these test conditions ?
Testmatch with Net 58573
Moderators: hgm, Rebel, chrisw
-
- Posts: 2872
- Joined: Wed Mar 08, 2006 10:09 pm
- Location: Germany
- Full name: Werner Schüle
Testmatch with Net 58573
Werner
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: Testmatch with Net 58573
Hard to say. Are these 40/20' real 20 minutes time control for 40 moves, or adjusted "20 minutes"? If they are real, it's quite a lot of time per move, and it might be that even on GTX 1650 with its fp-16 larger T40 would be better. A close call, I would think.Werner wrote: ↑Thu Dec 12, 2019 12:10 pm Hi,
I played 100 games against Stockfish 10 x64 1CPU under CEGT 40/20 conditions. Grafikcard is GTX 1650:
1 LCZero 0.23.1 Cuda (58573) +45 +23/=67/-10 56.50% 56.5/100
2 Stockfish 10.0 x64 1CPU -45 +10/=67/-23 43.50% 43.5/100
I ask me: are larger networks really better under these test conditions ?
-
- Posts: 2872
- Joined: Wed Mar 08, 2006 10:09 pm
- Location: Germany
- Full name: Werner Schüle
-
- Posts: 74
- Joined: Wed Dec 04, 2019 11:25 am
- Full name: Prasanna Bandihole
Re: Testmatch with Net 58573
I feel 6 series network plays much stronger than 5 series. Eventually, 6 series will prevail over 4 series.Werner wrote: ↑Thu Dec 12, 2019 12:10 pm Hi,
I played 100 games against Stockfish 10 x64 1CPU under CEGT 40/20 conditions. Grafikcard is GTX 1650:
1 LCZero 0.23.1 Cuda (58573) +45 +23/=67/-10 56.50% 56.5/100
2 Stockfish 10.0 x64 1CPU -45 +10/=67/-23 43.50% 43.5/100
I ask me: are larger networks really better under these test conditions ?