[PWGHF] Patches for first Xic autoencoder study

[macamerl]

Minimal changes in XicToPKPi specific files (task and selector) to evaluate the MSE between input (externally scaled) and internal scaled output of autoencoder. At moment, one can not run Autoencoder and BDT at the same time since they competitively fill candidate.mlProbXicToPKPi()[0].

[zhangbiao-phy]

Hi @macamerl, Thanks for the development! First of all, let me ping the code owner to see if they have any comments on this implementation. @mfaggin@cterrevo and @phymanshu. Then I only have a few comments, see the review. Then could you also fix magalinter errors since they come from this PR?

[phymanshu]

Hi @macamerl@zhangbiao-phy
Since you are adding a configurable for these studies, I have no problem as long as it is not conflicting with the standard BDT analysis.
Best wishes

[macamerl]

Thanks @phymanshu. Yes, I locally checked that the BDT inference has no problem after the changes that I made. The flags "applyMSE" and "applyMinMax" are set false/0 by default. In any case, I will privately send you the config file that I used for the check.

[vkucera]

Can you not avoid all the branching and just make the decision once?

[vkucera]

@macamerl Is there any progress?

[macamerl]

Hi, I'm implementing the comment received by @fgrosa . However, we had Italian national holidays as soon as after Easter and I had to replace one of my colleagues for other more urgent tasks of the project. Then, I have slowed down the debugging of the new version. I will give you an update next week.

[vkucera]

@macamerl Is there any activity on this?

[macamerl]

@vkucera Yes, I implemented the ideas (and small adjustment) in the offline mail in the old O2Physics version. it worked at the beginning of June. Now, I think to see some conflicts btw the onnx versions (see error below). Then, I decide to update my local O2Physics version and to arrive at the point that my branch works again.

I also attached an example of the error: "Schema error: Trying to register schema with name Abs (domain: version: 1) from file /local/workspace/DailyBuilds/DailyO2Physics-slc9/daily-tags.uO7Ig4H9DC/SOURCES/onnx/v1.17.0-alice2/v1.17.0-alice2/onnx/defs/math/old.cc line 2729, but it is already registered from file /local/workspace/DailyBuilds/DailyO2Physics-slc9/daily-tags.uO7Ig4H9DC/SOURCES/onnx/v1.17.0-alice2/v1.17.0-alice2/onnx/defs/math/old.cc

[vkucera]

@macamerl Your current branch does not show any development.

[macamerl]

What do you prefer? You want to close this commit request and open a new one when I solve the error (in the previous comment) in my local branch?

[vkucera]

What do you prefer? You want to close this commit request and open a new one when I solve the error (in the previous comment) in my local branch?

Please do not open a new PR. Just resolve the conflicts, address the comments and push the commits in your branch to update this PR.

[vkucera]

Hi @macamerl , there has been no update in two weeks and the PR has been opened for 3 months.
Is there any prospect of converging to a final PR?

[macamerl]

Please give me another week. I found that the previous errors came from the fact that O2 was updated. PWGHF changed few dependences. Then I'm running locally the new version with BDT. In these days, I'm rechecking the AE inference. I will commit when it is stable again.

[github-actions]

O2 linter results: ❌ 0 errors, ⚠️ 0 warnings, 🔕 0 disabled

[macamerl]

Sorry, before I did not want to close it

[github-actions]

This PR has not been updated in the last 30 days. Is it still needed? Unless further action is taken, it will be closed in 5 days.