Life In 19x19 http://www.lifein19x19.com/ |
|
New android app "BadukAI" http://www.lifein19x19.com/viewtopic.php?f=18&t=17784 |
Page 6 of 28 |
Author: | And [ Mon Oct 05, 2020 8:42 am ] |
Post subject: | Re: New android app "BadukAI" |
BadukAI (KG 10b, 3s/move) - CSDL 5d 1:1 (CS W +R, KG W +R) BadukAI (KG 10b, 4s/move) - CSDL 5d 1:1 (CS B +R, KG B +R) BadukAI (KG 10b, 5s/move) - CSDL 5d 0:2 (CS B +R, CS W +R) |
Author: | akigo [ Mon Oct 05, 2020 1:23 pm ] |
Post subject: | Re: New android app "BadukAI" |
I made a new version (0.8), which fixes the bug discovered by @And (see post #97). Thanks again for the help in analyzing the error. |
Author: | And [ Tue Oct 06, 2020 10:48 am ] |
Post subject: | Re: New android app "BadukAI" |
BadukAI (KG 10b, 8s/move) - CSDL 5d 3:1 (KG B +1.5, KG W +R, CS W +R, KG W +24.5) |
Author: | Amigo [ Tue Oct 06, 2020 1:04 pm ] |
Post subject: | Re: New android app "BadukAI" |
akigo, thanks a lot for KataGo for android! will you add Chinese rules soon? they are somehow more familiar to people ... ![]() |
Author: | akigo [ Thu Oct 08, 2020 11:49 am ] |
Post subject: | Re: New android app "BadukAI" |
I made a new version (0.9) with the following changes: 1) When AI passes, a popup message is displayed shortly, which informs about the pass 2) KataGo now uses chinese rules |
Author: | And [ Thu Oct 08, 2020 11:50 am ] |
Post subject: | Re: New android app "BadukAI" |
BadukAI (KG 10b, 10s/move) - CSDL 5d 8:2 (time parity) |
Author: | And [ Thu Oct 08, 2020 11:59 am ] |
Post subject: | Re: New android app "BadukAI" |
akigo wrote: I made a new version (0.9) with the following changes: 1) When AI passes, a popup message is displayed shortly, which informs about the pass 2) KataGo now uses chinese rules many many gratitude !!! |
Author: | And [ Thu Oct 08, 2020 12:47 pm ] |
Post subject: | Re: New android app "BadukAI" |
lightvector, akigo you make the world a better place and people happier! very pleasant program! ![]() |
Author: | Vargo [ Fri Oct 09, 2020 2:23 am ] |
Post subject: | Re: New android app "BadukAI" |
And wrote: BadukAI (KG 10b, 10s/move) - CSDL 5d 8:2 (time parity) I don't understand... With my smartphone (Exynos 990) , BadukAI KG 20b, 10s/move usually wins (as W) at H6 against CSDL 5d, H6 seems a fair handicap. KG 20b, 10s/move is several ranks stronger. CSDL 5d can't win 20% of its games in even games. I just tried 12 such even games, and predictably they all went rapidly the same way : after 50-70 moves, CSDL's winrate was always around 0. (For example, BadukAI is B in the 4 screenshots) |
Author: | go4thewin [ Fri Oct 09, 2020 5:17 am ] | ||
Post subject: | Re: New android app "BadukAI" | ||
I have the 6b net w/4 playouts (1 thread) stronger than gnugo (ogs 13k), the 10b policy network at around 3k, the 15b policy at 2-3 dan, the 20b policy at 4 dan, and the 40*256 bot policy at around 5 dan. The 10b at 9 payouts (1 thread) can beat the 15 bot policy. So it is a high kyu/low dan bot. The 20b is a high dan bot trained on 40b data. At 9 playouts, it is maybe 1 stone behind gtp4zen7 9dan. And what surprised me the most was that the 40b is the strongest at 5 sec/move on modern phones! attached is komi 9 game with 10b policy (black) winning against pachi at default settings on my pentium 4405u. I cannot get pachi to play as black because of some bug, but the result of this game is typical between the two.
|
Author: | And [ Fri Oct 09, 2020 8:42 am ] | |||
Post subject: | Re: New android app "BadukAI" | |||
Vargo screenshots of two games, BadukAI (KG 10b, 10s/move) - CSDL 5d. sgf did not save
|
Author: | akigo [ Fri Oct 09, 2020 10:17 am ] |
Post subject: | Re: New android app "BadukAI" |
At equal playouts the 20b network is about 1350 Elo stronger than the 10b network (see KataGo's README). At time parity we have to consider that the 10b network is about 8 times faster (at least on my device) due to the smaller size, so that the 10b network will have 8 times the number of playouts. Since doubling the playouts gains around 200 Elo (see https://github.com/leela-zero/leela-zero/issues/2236), this will reduce the gap by around 600 Elo. But we still have a whopping 750 Elo advantage for 20b at time parity. And the difference between @Vargo's and @And's configuration will be even larger, since @Vargo uses a faster device. So the difference in scores against CS is very plausible. |
Author: | And [ Fri Oct 09, 2020 12:02 pm ] |
Post subject: | Re: New android app "BadukAI" |
BadukAI (KG 15b, 10 playouts) - CS Zero 6d 1:0 (BadukAI W +18.5) BadukAI (KG 15b, 10 playouts) - CS Zero 7d 1:0 (BadukAI W +0.5) BadukAI KG 15b, 10 playouts ~ 15 sec/move Mobile Linpack 1.4 (https://play.google.com/store/apps/deta ... kbenchmark) threads:2 max:9.33 mflop/sec, threads:1 max:7.78 mflop/sec emulator nox Vargo can you see the speed of your device mflop/sec? |
Author: | And [ Fri Oct 09, 2020 12:55 pm ] |
Post subject: | Re: New android app "BadukAI" |
CSDL 5d usually thinks for 10 seconds regardless of the device. launched on the emulator CS 5d (1 core) - CS 5d (4 cores) 3:7 |
Author: | Vargo [ Fri Oct 09, 2020 10:25 pm ] |
Post subject: | Re: New android app "BadukAI" |
@And Hi, I use CSDL on my laptop (i7-9750H, 6 cores, 12 threads, Win 10) At 5dan, one move takes around 0.1 or 0.2 sec. For example, below is a screenshot of a complete 205 moves game (CSDL5d v. CSDL5d). Total time for the 205 moves was 29 sec (~0.14 sec/move) On my Ipad pro, at 5d, each move takes 5-10 sec, but the strength is the same as in the Win version. For the specifications of the Exynos 990 , see this site I'll make some tests with KG10b and CSDL. |
Author: | Vargo [ Sat Oct 10, 2020 5:25 am ] | |||
Post subject: | Re: New android app "BadukAI" | |||
Two games : BadukAI_KG_10b_10s/move v. CSDL 5d At H6, BadukAI_KG10b loses, H6 seems too much. At H4, BadukAI_KG10b wins The winrate graph for the H4 game (Mmmmmmmh...the board is rotated 180° ![]()
|
Author: | akigo [ Sat Oct 10, 2020 6:32 am ] |
Post subject: | Re: New android app "BadukAI" |
@And just for comparison I ran the Mobile Linpack 1.4 on my device (Snapdragon 855+): 1 Thread: max. 999 mflops/s 2 Threads: max. 1030 mflops/s And from geekbench 5 scores I know that @Vargo's Exynos 990 is still a little faster. |
Author: | go4thewin [ Sat Oct 10, 2020 8:18 am ] |
Post subject: | Re: New android app "BadukAI" |
snapdragon 625 1 thread >150 (1st reading), <174 when device first turns on. on this device 40*256 net is strongest at any time setting. Just to add another data point. 2nd device is Likebook mars e ink ereader processor=?. 1 thread <68.5 . Here, 20b takes maybe 4 seconds for 1 thread 1 playout policy move. |
Author: | And [ Sat Oct 10, 2020 8:52 am ] |
Post subject: | Re: New android app "BadukAI" |
akigo wrote: @And just for comparison I ran the Mobile Linpack 1.4 on my device (Snapdragon 855+): 1 Thread: max. 999 mflops/s 2 Threads: max. 1030 mflops/s And from geekbench 5 scores I know that @Vargo's Exynos 990 is still a little faster. Vargo 1 performance difference is more than 100! 2 engines work differently ("Crazy Stone has made a huge step forward by combining Deep Neural Networks with Monte Carlo Tree Search." https://play.google.com/store/apps/deta ... oid.gocsdl) how does the strength of their game change with performance? CSDL settings - 5d, and if its strength does not depend much on the device (it should not depend!) then everything is in order! Vargo wrote: ... On my Ipad pro, at 5d, each move takes 5-10 sec, but the strength is the same as in the Win version... 3 just a few games given this, no results will surprise me! are you still surprised? ![]() |
Author: | And [ Sat Oct 10, 2020 12:51 pm ] | |||
Post subject: | Re: New android app "BadukAI" | |||
the program hangs at the end of the game. I could not get out of this state. saved sgf, does not react to anything else. if necessary, there is a log. this happened for the first time, does not bother, I inform you just in case
|
Page 6 of 28 | All times are UTC - 8 hours [ DST ] |
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group http://www.phpbb.com/ |