Spaces:
Sleeping
Sleeping
Commit History
-
Change automated training interval from 2 minutes to 1 day
Senum2001461c5a6 -
Fix root cause: Parse JSON strings from Supabase before accessing as dictionaries
Senum2001835975d -
Fix syntax error: correct indentation for try-except block in run_training_cycle
Senum200149a9e96 -
Add comprehensive error handling and traceback logging to identify str.get() error source
Senum200190d4f4d -
Deep fix: Add comprehensive state validation before logging training cycles to prevent type errors
Senum200168c41e5 -
Add automated training scheduler - checks every 2 minutes and trains when 10+ feedback samples available
Senum2001a023a85 -
Fix: safe extraction of version_id to avoid attribute errors when version state is string
Senum2001376e494 -
Fix all dictionary access errors in feedback pipeline with proper type checks
Senum20017fff18d -
Add graceful handling for missing database tables in model versioning
Senum2001388bcdc -
Fix error handling in feedback pipeline for model versioning
Senum20015de9e01 -
Add model versioning and training history tracking system
Senum200101d0daa
-
Add feedback learning pipeline for continuous model improvement
Senum200130b81fd
-
Add severity-based color coding for bounding boxes with confidence-scaled intensity
Senum200160def4f
-
Add confidence scores to bounding box detections
Senum2001f83c0b7
-
Implement complete classification with all detection rules - Point/Tiny/Wire/Loose Joint detection
Senum2001f301e7a -
Fix image download to preserve format and add classification debugging
Senum2001de87a47 -
Add open-clip-torch dependency for anomalib VLM models
Senum20017c16ab2 -
Fix Dockerfile: Add --user flag, ca-certificates, and improve gdown with --fuzzy flag
Senum2001f6c038a -
Fix: Add python-dotenv dependency and fix matplotlib permissions with non-root user
Senum2001eba5a08 -
Optimize Docker image - Use CPU-only PyTorch and minimal dependencies to reduce size
Senum20013b2a8b5 -
Deploy Anomaly Detection API
Senum20019cf599c -
initial commit
8a7ddf0