Architecture Doctor¶
Automated SNN diagnostics: coding efficiency, hardware fit, spike health, actionable recommendations.
from sc_neurocore.doctor import ArchitectureDoctor
doc = ArchitectureDoctor()
report = doc.diagnose(model)
for issue in report.issues:
print(f"[{issue.severity}] {issue.message}")
See Tutorial 56: Architecture Doctor.
sc_neurocore.doctor
¶
Automated SNN architecture diagnostics: coding efficiency, hardware fit, spike health, and actionable fix recommendations.
Diagnosis
dataclass
¶
Single diagnostic finding.
Source code in src/sc_neurocore/doctor/diagnose.py
33 34 35 36 37 38 39 40 41 | |
DiagnosticReport
dataclass
¶
Full diagnostic report for an SNN architecture.
Source code in src/sc_neurocore/doctor/diagnose.py
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | |
score
property
¶
Health score 0-100. 100 = no issues.