NNUE Research Project

[dkappe]

What is a “fetish giving female name?” Is this something you want to share?

I don't want to share anything with you. Learned my lesson about you and your arrogant attitude long time ago.
"The joy of seeing Bagatur (or whatever it’s called) play asymptote will be boundless".

You mentioned that Igel 2.9 was different from <= 2.8. I tried to clarify why that might be. Then you said something about gender and fetish which I didn’t understand. Incidentally, “Night Nurse” by Jamaican artist Gregory Isaacs is about love in the face of serious illness. Bad Gyal, a mcts/nn net from which night nurse is trained, is named after a Spanish reggaeton artist. I guess night nurse would probably be similar to Fat Fritz 2 as the origins of the data are similar.

[dkappe]

You have serious comprehension problems. Did you try at least to completely read Andreas first post?
(We know your main expertise is a kind of childish trolling, but still...)

Here is the part you cut off and 'replied' too. Ofc you have to look at remark #2 otherwise it makes no sense to reply at all...

RubiChess wrote:
Fri Mar 12, 2021 12:35 pm
Observation/remark #2 looks strange. Talks about Igel-2.7/2.8 but then switches to Fat Fritz 2 instead of Igel-2.9 (which looks different from <=2.8).

Regards, Andreas

I simply noted the difference between the networks in Igel <= 2.8 and Igel 2.9. Then Andreas said something about gender and fetish, which I didn’t understand.

[Rebel]

I updated the page.

It would be great if you could also update the Orion 0.7 part (see my previous comment in this thread : in short, rename "Orion 0.7" with "Orion 0.7 NNUE" and I confirm that the network used by this experimental and not official version of Orion was the SF12's one, hence the high expected similarity )

A great thank !

Consider it done!

[Rebel]

NNUE Research Project
March 10, 2021

It´s generally known by now similarity testing on moves does not work with NNUE nets. On this page we will try to research if it is not possible using other methods. One method is to calculate the Root-mean-square deviation (or RMS) of the scores instead of moves as after all NNUE is a set of scores. We will present data and the source code for discussion.

Let´s start at the beginning of NNUE in the summer of 2020 the starting point of the NNUE revolution when the Stockfish team implemented the Sergio nets. Our first goal is to measure the stability of the RMS of Stockfish NNUE nets. From the Sergio nets we calculate the RMS of the very first 3 nets (july) and the last 3 (september) and compare the RMS with the final SF12 net, see table one. In table two the nets between SF12 and SF13 are compared plus 5 nets after the release of SF13.

....

http://rebel13.nl/home/nnue.html

Observation/remark #2 looks strange. Talks about Igel-2.7/2.8 but then switches to Fat Fritz 2 instead of Igel-2.9 (which looks different from <=2.8).

Regards, Andreas

Igel author states 2.9 is an own net contrary to 2.7 and 2.8

Webpage:
Two versions of Igel: 2.7.0 and 2.8.0 are excluded from network training/data generation process (both for data and for validation data) because they use Dietrich Kappe's Night Nurse network

[Rebel]

Regarding the questions, I compiled a download with all the epd files at http://rebel13.nl/nnue-epd.7z

Contents:

Code: Select all

11-03-2021  19:58    <DIR>          .
11-03-2021  19:58    <DIR>          ..
11-03-2021  19:54    <DIR>          ff2
04-03-2021  08:59           647.686 Nemorino.epd
09-03-2021  22:18           644.556 Orion_0.8.epd
08-03-2021  12:18           649.858 SF12-Igel-270.epd
08-03-2021  12:35           649.635 SF12-Igel-280.epd
08-03-2021  21:18           652.073 SF12-Igel-290.epd
08-03-2021  12:53           652.728 SF12-Minic.epd
08-03-2021  13:11           653.371 SF12-napping-nexus.epd
08-03-2021  13:29           650.594 SF12-nascent-nutrient.epd
09-03-2021  11:03           652.710 SF12-Orion_0.7.epd
08-03-2021  13:46           652.583 SF12-sf-0c6fc5ef48e1.epd
08-03-2021  17:44           652.711 SF12-sf-516f5b95189a.epd
08-03-2021  17:27           652.513 SF12-sf-dd0c4c630f7e.epd
09-03-2021  09:40           652.457 SF12-sv-20200720-1017.epd
09-03-2021  10:00           652.411 SF12-sv-20200721-0909.epd
09-03-2021  10:20           652.651 SF12-sv-20200721-1432.epd
09-03-2021  10:38           652.882 SF12-sv-20200906-1046.epd
09-03-2021  10:56           652.892 SF12-sv-20200908-1733.epd
09-03-2021  11:15           652.759 SF12-sv-20200914-1520.epd
08-03-2021  11:43           652.698 SF12.epd
08-03-2021  21:35           651.330 SF13-Igel-290.epd
08-03-2021  23:30           652.440 SF13-Rubi-2.01.epd
09-03-2021  09:06           651.983 SF13-sf-6b7a4192c303.epd
09-03-2021  09:26           651.878 SF13-sf-94816594b327.epd
08-03-2021  12:01           652.459 SF13.epd

Remarks:
1. nets are tested as much as possible with SF12 and SF13.
2. Nemorino and Orion 0.8 are the exceptions since they have a different file format.
3. The Orion 0.7 version has the exact SF12 net.
4. the folder ff2 contains the epd's of sf12, 13 and ff2 at 100ms, 250 and 500ms, made by someone else on a different pc.
5. epd's labelled with "sv" are the tested "sergio" nets.
6. epd's labelled with "sf" are Stockfish nets.

Under folder ff2:
FF2-100ms.epd is the output when ff2 engine uses the ff2 net?

Yes, out of the box.

What is SF12-100ms.epd?

To calculate the RMS and SIM -

Code: Select all

sim-score ff2-100ms.epd sf12-100ms.epd
sim-score ff2-100ms.epd sf13-100ms.epd

sim-score ff2-250ms.epd sf12-250ms.epd
sim-score ff2-250ms.epd sf13-250ms.epd

sim-score ff2-500ms.epd sf12-500ms.epd
sim-score ff2-500ms.epd sf13-500ms.epd

[RubiChess]

Observation/remark #2 looks strange. Talks about Igel-2.7/2.8 but then switches to Fat Fritz 2 instead of Igel-2.9 (which looks different from <=2.8).

Regards, Andreas

Igel author states 2.9 is an own net contrary to 2.7 and 2.8

Webpage:
Two versions of Igel: 2.7.0 and 2.8.0 are excluded from network training/data generation process (both for data and for validation data) because they use Dietrich Kappe's Night Nurse network

As I said in some other post: My original post was not so much about the Igel nets but about your text not mentioning Igel-2.9 (although it is in your table and looks different) but instead talking about Fat Fritz 2 which seems unrelated.
But maybe I just missed something, my english is far from perfect.

Regards, Andreas

[Rebel]

Observation/remark #2 looks strange. Talks about Igel-2.7/2.8 but then switches to Fat Fritz 2 instead of Igel-2.9 (which looks different from <=2.8).

Regards, Andreas

Igel author states 2.9 is an own net contrary to 2.7 and 2.8

Webpage:
Two versions of Igel: 2.7.0 and 2.8.0 are excluded from network training/data generation process (both for data and for validation data) because they use Dietrich Kappe's Night Nurse network

As I said in some other post: My original post was not so much about the Igel nets but about your text not mentioning Igel-2.9 (although it is in your table and looks different) but instead talking about Fat Fritz 2 which seems unrelated.
But maybe I just missed something, my english is far from perfect.

Regards, Andreas

I see what you mean now.

2. The current data implies that the Igel NNUE (version 2.70 and 2.80) with a RMS above 100 and a SIM of 30-35 is dissimilar to the Stockfish nets, the latter stated on the Igel website. However the Fat Fritz 2 data implies the opposite, showing strongest similarity of engines we tested to date with Stockfish nets.

The bold part is the essence.

[Guenther]

Observation/remark #2 looks strange. Talks about Igel-2.7/2.8 but then switches to Fat Fritz 2 instead of Igel-2.9 (which looks different from <=2.8).

Regards, Andreas

Igel author states 2.9 is an own net contrary to 2.7 and 2.8

Webpage:
Two versions of Igel: 2.7.0 and 2.8.0 are excluded from network training/data generation process (both for data and for validation data) because they use Dietrich Kappe's Night Nurse network

As I said in some other post: My original post was not so much about the Igel nets but about your text not mentioning Igel-2.9 (although it is in your table and looks different) but instead talking about Fat Fritz 2 which seems unrelated.
But maybe I just missed something, my english is far from perfect.

Regards, Andreas

Neither 'rebel' nor dkappe are able to read your post til the end lol (remark #2 seems to be foreign for them...)
The level of this forum is so low meanwhile that we need to full quote for those people.

2. The current data implies that the Igel NNUE (version 2.70 and 2.80) with a RMS above 100 and a SIM of 30-35 is dissimilar to the Stockfish nets, the latter stated on the Igel website. However the Fat Fritz 2 data implies the opposite, showing strongest similarity of engines we tested to date with Stockfish nets.

So what is the meaning of the sudden FF2 comparison/appearance in the Igel remark? This was Andreas' understandable question.

[Rebel]

Observation/remark #2 looks strange. Talks about Igel-2.7/2.8 but then switches to Fat Fritz 2 instead of Igel-2.9 (which looks different from <=2.8).

Regards, Andreas

Igel author states 2.9 is an own net contrary to 2.7 and 2.8

Webpage:
Two versions of Igel: 2.7.0 and 2.8.0 are excluded from network training/data generation process (both for data and for validation data) because they use Dietrich Kappe's Night Nurse network

As I said in some other post: My original post was not so much about the Igel nets but about your text not mentioning Igel-2.9 (although it is in your table and looks different) but instead talking about Fat Fritz 2 which seems unrelated.
But maybe I just missed something, my english is far from perfect.

Regards, Andreas

Neither 'rebel' nor dkappe are able to read your post til the end lol (remark #2 seems to be foreign for them...)
The level of this forum is so low meanwhile that we need to full quote for those people.

2. The current data implies that the Igel NNUE (version 2.70 and 2.80) with a RMS above 100 and a SIM of 30-35 is dissimilar to the Stockfish nets, the latter stated on the Igel website. However the Fat Fritz 2 data implies the opposite, showing strongest similarity of engines we tested to date with Stockfish nets.

So what is the meaning of the sudden FF2 comparison/appearance in the Igel remark? This was Andreas' understandable question.

Bullies are ignored.

[Ferdy]

Regarding the questions, I compiled a download with all the epd files at http://rebel13.nl/nnue-epd.7z

Contents:

Code: Select all

11-03-2021  19:58    <DIR>          .
11-03-2021  19:58    <DIR>          ..
11-03-2021  19:54    <DIR>          ff2
04-03-2021  08:59           647.686 Nemorino.epd
09-03-2021  22:18           644.556 Orion_0.8.epd
08-03-2021  12:18           649.858 SF12-Igel-270.epd
08-03-2021  12:35           649.635 SF12-Igel-280.epd
08-03-2021  21:18           652.073 SF12-Igel-290.epd
08-03-2021  12:53           652.728 SF12-Minic.epd
08-03-2021  13:11           653.371 SF12-napping-nexus.epd
08-03-2021  13:29           650.594 SF12-nascent-nutrient.epd
09-03-2021  11:03           652.710 SF12-Orion_0.7.epd
08-03-2021  13:46           652.583 SF12-sf-0c6fc5ef48e1.epd
08-03-2021  17:44           652.711 SF12-sf-516f5b95189a.epd
08-03-2021  17:27           652.513 SF12-sf-dd0c4c630f7e.epd
09-03-2021  09:40           652.457 SF12-sv-20200720-1017.epd
09-03-2021  10:00           652.411 SF12-sv-20200721-0909.epd
09-03-2021  10:20           652.651 SF12-sv-20200721-1432.epd
09-03-2021  10:38           652.882 SF12-sv-20200906-1046.epd
09-03-2021  10:56           652.892 SF12-sv-20200908-1733.epd
09-03-2021  11:15           652.759 SF12-sv-20200914-1520.epd
08-03-2021  11:43           652.698 SF12.epd
08-03-2021  21:35           651.330 SF13-Igel-290.epd
08-03-2021  23:30           652.440 SF13-Rubi-2.01.epd
09-03-2021  09:06           651.983 SF13-sf-6b7a4192c303.epd
09-03-2021  09:26           651.878 SF13-sf-94816594b327.epd
08-03-2021  12:01           652.459 SF13.epd

Remarks:
1. nets are tested as much as possible with SF12 and SF13.
2. Nemorino and Orion 0.8 are the exceptions since they have a different file format.
3. The Orion 0.7 version has the exact SF12 net.
4. the folder ff2 contains the epd's of sf12, 13 and ff2 at 100ms, 250 and 500ms, made by someone else on a different pc.
5. epd's labelled with "sv" are the tested "sergio" nets.
6. epd's labelled with "sf" are Stockfish nets.

Under folder ff2:
FF2-100ms.epd is the output when ff2 engine uses the ff2 net?

Yes, out of the box.

What is SF12-100ms.epd?

To calculate the RMS and SIM -

Code: Select all

sim-score ff2-100ms.epd sf12-100ms.epd
sim-score ff2-100ms.epd sf13-100ms.epd

sim-score ff2-250ms.epd sf12-250ms.epd
sim-score ff2-250ms.epd sf13-250ms.epd

sim-score ff2-500ms.epd sf12-500ms.epd
sim-score ff2-500ms.epd sf13-500ms.epd

There is also a file named SF12.epd, outside the ff2 folder, what is the difference between this file and SF12-100ms.epd in the ff2 folder?