Pipeline complet Radiacode 103 - identification automatique d'isotopes

- VegaModel CNN-FCNN 34.5M params, 82 isotopes, val acc 99.89%
- Generation 50k spectres synthetiques 1D (12-24h durees)
- Entrainement 100 epochs sur RTX 5060 Ti (CUDA 12.8, Blackwell)
- Detection continue avec soustraction du background
- Capture background 24h avec gestion deconnexion
- Docker Compose : conteneur train (GPU) + detect (CPU/USB)
- Modele entraite inclus (vega_best.pt, 395 Mo)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Jacquin Antoine
2026-05-19 12:29:56 +02:00
commit 745a64b342
52 changed files with 17558 additions and 0 deletions

40
.gitignore vendored Normal file
View File

@ -0,0 +1,40 @@
# Modeles entraines
models/vega_epoch_*.pt
models/vega_final.pt
# Donnees synthetiques (4+ Go)
data/synthetic/
# Background (genere en cours de capture)
data/background_24h.npy
data/background_snapshot.json
# Logs
logs/*.log
logs/*.json
# Python
__pycache__/
*.pyc
*.pyo
*.egg-info/
.eggs/
dist/
build/
*.egg
# Docker
*.tar
# IDE
.vscode/
.idea/
*.swp
*.swo
# OS
.DS_Store
Thumbs.db
# Environnement
.env