Free · No signup · Client-side

Dataset class-balance checker

Paste your COCO JSON or YOLO labels, see per-class counts and the imbalance ratio. Catch a dominant-class problem before you waste a training run.

Only categories and annotations are read; segmentation / keypoints ignored.

Severely imbalanced (ratio 14.0:1). Minority classes will under-train. Augment + class-weighted loss recommended.
Classes
4
Annotations
17
Most
14
Least
1
Max:Min
14.0:1
person
14 (82.4%)
helmet
1 (5.9%)
safety_vest
1 (5.9%)
forklift
1 (5.9%)

Why class balance matters

Object-detection models trained on imbalanced datasets confidently over-predict the majority class and quietly miss the minority ones. A 50:1 ratio is enough to make a model functionally ignore the rare class — even if your overall mAP looks decent.

Rough thresholds:

  • max:min ≤ 3 — balanced; no intervention needed.
  • max:min 3-10 — moderate; class-weighted loss or balanced sampling usually fixes it.
  • max:min > 10 — severe; combine augmentation, class-weighted loss, and (if possible) more labels of the rare class.
  • min == 0 — broken; you can't train a class you have zero labels for.

The fastest fix for severe imbalance: target the rare class with zero-shot detection to find more candidates, then run them through auto-labelling and active learning to expand the rare-class label pool.

Class balance — built into mSightFlow projects

This browser tool checks one snapshot. The platform monitors balance continuously and fires alerts:

# GET .../quality/alerts surfaces class-imbalance alerts among other QA signals
import os, requests
alerts = requests.get(
    "https://api.msightflow.ai/v1/projects/PROJECT_ID/quality/alerts",
    headers={"Authorization": f"Bearer {os.environ['MSF_API_KEY']}"},
).json()

for a in alerts["alerts"]:
    print(f"[{a['severity']}] {a['type']}: {a['message']}")
# → [warning] class_imbalance: 'person' has 45× more samples than 'helmet'

Sibling tools

Continuous class-balance monitoring.

Free in every mSightFlow tier — annotation quality + IAA + class-balance alerts run on your projects automatically.