← Back to Notes

How I Improved CNN Accuracy

A short write-up on what actually moved accuracy: augmentation, architecture tweaks, and schedule discipline.

CNN Training Augmentation

What was the baseline?

I started with a standard CNN and tracked loss/accuracy per epoch. Early results improved fast, then plateaued.

Result (tracked)

  • Training: ran up to 400 epochs
  • Peak training accuracy: ~96.6%
  • Note: training accuracy ≠ test accuracy. I use it to track stability + overfitting, then confirm on evaluation splits.

What actually improved accuracy

  • Better data augmentation (flip/rotation/crop) to reduce overfitting
  • BatchNorm to stabilize deeper training
  • Dropout to improve generalization
  • Learning rate schedule to keep progress after plateaus

My final training habits

  • Save curves and compare runs (don’t trust “feels better”)
  • Change one thing at a time
  • Long training only after the setup is stable

One takeaway

Most gains came from being systematic: augmentation + stability + schedule — not “random architecture hype”.