Concepts

These explanations dive into the what, why and theory behind each of DataEval’s features.

• Bayes Error Rate Estimation

• Cluster Assignment

• Coverage Analysis

• Detecting Bias in Datasets

• Cleaning Datasets

• Evaluating Parity

• Evaluating Label Parity

• Dataset Divergence

• Detecting Drift in Datasets

• Detecting Duplicates

• Image Statistics Functions

• Outliers Class

• Model Training Techniques

• Detecting Out of Distribution Data

• Sufficiency of Datasets per Model

• Upperbound on Average Precision Estimation

• Balance Bias Metrics

• Diversity Indices

For a quick reference of each algorithm’s functionality and requirements, see the Algorithm Overview page.

Algorithm Overview