Writing
Engineering notes from real projects.
Short, evidence-based write-ups about what went wrong, how I found it, and what I would do differently.
The checkpoint bug that changed my reported model
My diabetic retinopathy model reported 95.2% test accuracy, and the notebook said it came from the best-validation epoch. One missing copy meant it did not. What happened, how I found it, and what the number really means.
- PyTorch
- Model evaluation
- Reproducibility
What Grad-CAM revealed about shortcut learning
Explanation methods are meant to show whether a model looks at the right place. In two medical-imaging projects they raised real questions about my models, and once, through a colour bug, nearly pointed me to the wrong conclusion.
- Explainable AI
- Grad-CAM
- LIME
- Medical imaging

