Reference Guide

Detectors

Detectors can determine if a dataset or individual images in a dataset are indicative of a specific issue

• Drift Detection
• Duplicates Detection
• Linter
• Out-of-Distribution Detection

Metrics

Metrics are a way to measure the performance of your models or datasets that can then be analyzed in the context of a given problem

• Bayes Error Rate
• Divergence
• Parity
• Image Statistics
• Channel Statistics
• Image Flags
• Upperbound Average Precision

Workflows

Workflows perform a sequence of actions to analyze the dataset and make predictions

• Sufficiency

Supported Model Backends

The models and model trainers provided by DAML are meant to assist users in setting up architectures that are guaranteed to work with applicable DAML metrics.
Below is a list of backends with available trainers and models.

• PyTorch Models
• Tensorflow Models