Notebooks

Prepackaged Inference Server Examples

• Deploy a Scikit-learn Model Binary
• Deploy a Tensorflow Exported Model
• MLflow Pre-packaged Model Server A/B Test
• Deploy a XGBoost Model Binary
• Deploy Pre-packaged Model Server with Cluster's MinIO

Python Language Wrapper Examples

• SKLearn Iris Classifier
• Sagemaker SKLearn Example
• TFserving MNIST
• Statsmodels Holt-Winter's time-series model
• Runtime Metrics & Tags

Specialised Framework Examples

• NVIDIA TensorRT MNIST
• OpenVINO ImageNet
• OpenVINO ImageNet Ensemble

Incubating Projects Examples

• Kubeflow Seldon E2E Pipeline
• H2O Java MoJo
• Outlier Detection with Combiner
• Stream Processing with KNative Eventing
• Kafka CIFAR10

Cloud-Specific Examples

• AWS EKS Tensorflow Deep MNIST
• Azure AKS Tensorflow Deep MNIST
• GKE with GPU Tensorflow Deep MNIST
• Alibaba Cloud Tensorflow Deep MNIST

Advanced Machine Learning Insights

• Real time monitoring of statistical metrics
• Tabular, Text and Image Model Explainers
• Outlier Detection on CIFAR10

Batch Processing with Seldon Core

• Batch Processing with Argo Workflows
• Batch Processing with Kubeflow Pipelines

MLOps: Scaling and Monitoring and Observability

• Autoscaling Example
• Request Payload Logging with ELK
• Custom Metrics with Grafana & Prometheus
• Distributed Tracing with Jaeger
• CI / CD with Jenkins Classic
• CI / CD with Jenkins X
• Replica control

Production Configurations and Integrations

• Example Helm Deployments
• Max gRPC Message Size
• REST timeouts
• Deploy Multiple Seldon Core Operators
• Protocol Examples
• Custom Protobuf Data Example

Complex Graph Examples

• Chainer MNIST Model Deployment
• Test using Minikube

Ingress

• Ambassador Canary
• Ambassador Shadow
• Ambassador Headers
• Ambassador Custom Config
• Istio Canary
• Istio Examples

Infrastructure

• Patch Volumes for Version 1.2.0 Upgrade

Benchmarking and Load Tests

• Service Orchestrator
• Tensorflow
• Benchmarking with Argo Worfklows & Vegeta
• Setup
• Create GRPC benchmark with GHZ and Argo Workflows
• Run a set of tests
• Deeper Analysis