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
- Forward Pass, Loss, Backward, Step
- Write a Minimal Training Loop
- Track Accuracy While You Train
- Train vs Eval Mode