0PricingLogin
Deep Learning Academy · Lesson

Track Accuracy While You Train

Turn predictions into a score.

Loss Alone Lies a Little

A falling loss feels good, but it is abstract. To know if your model is truly useful you also want accuracy, the share of predictions it gets right. 🎯

From Logits to a Choice

Your model outputs raw scores per class. To pick a prediction you take the index of the largest score with argmax along the class dimension.

preds = pred.argmax(dim=1)

All lessons in this course

  1. Forward Pass, Loss, Backward, Step
  2. Write a Minimal Training Loop
  3. Track Accuracy While You Train
  4. Train vs Eval Mode
← Back to Deep Learning Academy