Evaluation

What is ML evaluation?

ML evaluation scores model or pipeline outputs against labels or a judge, so you can compare versions.

Updated

How it works

  • Fix the inputs at a table version.
  • Score the output columns.
  • Compare scores across versions.

What it is not

It is not the database that stores those outputs. An eval framework is not a multimodal table.

ML evaluation: this, and the thing it is confused with

ML evaluation: this, and the thing it is confused with
ThisNot this
ScoresOutputsThe storage engine
NeedsLabels or a judgeOnly a metric name
Lives besideThe table of outputsInstead of the table

Where Pixeltable fits

Pixeltable stores the outputs you score. It is not an eval product. A score can still be a column or an external judge reading the table.

Questions

How does ML evaluation work?
Fix the inputs at a table version. Score the output columns. Compare scores across versions.
What is ML evaluation often confused with?
It is not the database that stores those outputs. An eval framework is not a multimodal table.