ML Models


The following tutorials focus on Wallaroo observability features including model drift and anomaly detection.


Model Drift Detection for Edge Deployments

How to detect model drift in Wallaroo Run Anywhere deployments using the house price model as an example.

Wallaroo Model Observability: Anomaly Detection

How to detect anomalous model inputs or outputs using the CCFraud model as an example.

Wallaroo Edge Computer Vision Observability

A demonstration on observability with computer vision deployed on edge devices.

Wallaroo Model Observability: Dashboard Metrics for Classification Models

How to retrieve metrics for inference performance from Wallaroo.

Wallaroo Model Observability: Dashboard Metrics for Summarization Models

How to retrieve metrics for inference performance from Wallaroo.

Wallaroo Edge Observability with Classification Financial Models

A demonstration on publishing an a Classification Financial model with Edge Observability through Wallaroo.

Wallaroo Edge Observability with Classification Financial Models through the Wallaroo MLOps API

A demonstration on publishing an a Classification Financial model with Edge Observability through the Wallaroo MLOps API.

Wallaroo Edge Observability with Wallaroo Assays

A demonstration on deploying a Wallaroo Pipeline as a Wallaroo Server edge deployment, and using the inference data for assays.

Model Observability with Assays

How to use Wallaroo Assays to monitor the environment and know when to retrain the model based on changes to data.

Edge Observabilty with No/Low Connection Tutorial

A demonstration model deployments on edge location with low or no connectivity.