Skip to content
ENExplore Calculators

mAP (Mean Average Precision) Calculator

Work out map (mean average precision) instantly with clear inputs, formula shown and shareable results.

About mAP (Mean Average Precision) Calculator

Average precision is the area under one class's precision-recall curve; mean average precision is the unweighted mean of those per-class values. Because the mean is unweighted, a rare class with poor AP drags the score down as much as a common one, which is exactly what makes mAP a useful test of balanced detection quality.

Formula

Mean average precision

mAP = (1/C) x sum of AP for each class c

C
Number of classes
AP
Area under that class's precision-recall curve

Worked example

With the default values below, mAP (Mean Average Precision) Calculator returns Mean average precision of 0.7400. Change any input above and every figure here is recalculated in your browser.

Inputs used

Average precision per class (comma separated)
0.82, 0.74, 0.65, 0.91, 0.58
IoU threshold usedaccepts 0.05–0.95
0.5

Results

Mean average precision
0.7400
Classes averaged
5
Best class AP
0.9100
Worst class AP
0.5800

Step by step

  1. 1Values used
  2. 2Mean average precision
  3. 3Mean average precision= 0.7400
  4. 4Classes averaged= 5
  5. 5Best class AP= 0.9100
  6. 6Worst class AP= 0.5800

Assumptions and limits

  • The result is derived only from the 2 inputs listed above. Anything not among them is not part of the calculation.
  • In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
  • Figures are rounded for display to 4 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Why does mAP drop when I add a rare class?

Every class contributes equally regardless of instance count, so a class with 20 examples and AP 0.2 pulls the mean down as hard as a class with 20,000 examples.

Should I quote mAP at a single IoU?

State the threshold explicitly. mAP@0.5 is far more forgiving than mAP@[.5:.95] and the two are not comparable.

Related Calculators

mAP (Mean Average Precision) Calculator | Calcrivo