Integrate Machine Learning into Your Spring Application in Less than an Hour
summary
Shows how to drop Deep Java Library (DJL) into a Spring Boot app, containerize with Jib, and run an image‑recognition microservice on Kubernetes or Pivotal Cloud Foundry using MXNet, PyTorch or TensorFlow engines. Demonstrates switching engines at build time, loading from a model zoo (70+ models), and running batch inference with Spark (800M records in ~6 hours). Reports real gains: 85% faster batch jobs (24h → 3.5h) and live demos where swapping engines improved detection accuracy.
AI-written summary · about
chapters (7)
- 0:00Introduction and speakers
- 0:53Overview of DJL
- 7:12DJL features and benefits
- 16:54Real-world use cases
- 24:54Spring Boot integration demo
- 45:12Future roadmap and resources
- 49:40Closing remarks
related talks
44mDeep Learning with DeepLearning4J and Spring Boot
29mAchieve real-time inference at scale on AWS with Deep Java Library
47mML in Java, YES it's possible!
27mDeveloping and Deploying ML Models with Java
46mML in Java, YES it's possible!
34mFast-Track Your AI-ML Model Integration
50mML in Java, YES it's possible!
01h 02mEnabling High Throughput, Low Latency Inference for Your AI Applications