[Rspamd-Users] Neural Question

[christian]

Hello,
after the neural "max_trains = 100" has been trained, a process "rspam: 
lua process: ANN train for SHORT/default" starts and uses a CPU core to 
100% permanently.


New emails are learned until 100 entries are stored:

2024-07-13 18:41:32 #729426(controller) <duy5w5>; neural; 
neural.lua:707: cannot learn ANN rn_SHORT_default_bioioq5b_0 now: there 
are not enough ham learn vectors (has {[spam] = 39, [ham] = 34} vectors; 
100 required)
2024-07-13 18:41:32 #729426(controller) <duy5w5>; neural; 
neural.lua:707: cannot learn ANN rn_LONG_default_bioioq5b_0 now: there 
are not enough ham learn vectors (has {[spam] = 351, [ham] = 297} 
vectors; 1000 required)


After this process has been started, no more SHORT:default entries 
appear in the log. No emails are tagged either. It seems as if the 
neural function freezes after reaching the 100 limit. It is the same 
with the LONG with a value of 100. After reaching this limit, a process 
starts which then constantly uses the CPU to its full capacity.

I have already reset the redis entries and re-trained them, but it 
happens again.


This occurred under 3.8.4 but now also under 3.9.0.


Christian


My neural Setup:

rspamadm configdump neural
*** Section neural ***
servers = "127.0.0.1:6379";
rules {
     LONG {
         ann_expire = 8640000;
         symbol_spam = "NEURAL_SPAM_LONG";
         symbol_ham = "NEURAL_HAM_LONG";
         train {
             max_iterations = 25;
             learning_rate = 0.010000;
             max_trains = 1000;
             max_usages = 200;
         }
     }
     SHORT {
         ann_expire = 86400;
         symbol_spam = "NEURAL_SPAM_SHORT";
         symbol_ham = "NEURAL_HAM_SHORT";
         train {
             max_iterations = 25;
             learning_rate = 0.010000;
             max_trains = 100;
             max_usages = 2;
         }
     }
}
enabled = true;
timeout = 120;

*** End of section neural ***