0PricingLogin
Deep Learning Academy · Lesson

Split Train, Validation & Test

Why you need three sets, not one.

One Pile Is Not Enough

If you train and judge a model on the same data, you only learn that it memorized those rows. To trust it, you must split your data into separate roles.

Meet the Training Set

The training set is the data your model actually learns from. Its weights are nudged again and again to fit exactly these examples well.

All lessons in this course

  1. Split Train, Validation & Test
  2. An Epoch Loop with Validation
  3. Save & Load with state_dict
  4. Early Stopping on Val Loss
← Back to Deep Learning Academy