Ready, Set, Go for K8s at edge today for AI/ML with Tensorflow
summary
Prototype deploys Kubernetes all-in-one at edge for IoT, uses MQTT into Artemis + Kafka + Camel K for ingestion and mediation, stores training data in Ceph and builds models with Jupyter and TensorFlow/TensorFlow Lite. Serving runs a Python TensorFlow autoencoder with MSE threshold for real‑time anomaly detection; Prometheus scrapes scores and Alertmanager fires webhooks for remediation. Design supports cloud control plane with Quay registry image replication to edge nodes and is validated as a working prototype.
AI-written summary · about
chapters (3)
related talks
45mAIoT Ops - Using Kubernetes and ML Ops to Build Edge ML Applications
24mDemo of Kubernetes at the Edge for AI Model Deployments
26mMachine Learning Meets K8s
27mHarnessing Kubernetes for Scalable AI/ML Workloads
42mDeploying ML at Scale with Kubernetes and TFX
42mKubernetes for Machine Learning: Managing and Scaling AI Workloads
46mDeploying scalable Machine Learning models with Kubernetes
55mUsing TensorFlow for Performing Deep Learning at the Edge