Practical AI Deploying models (to tractors 🚜)
Mar 1, 2022
Alon Klein Orback, CTO of GreenEye, and Moses Guttmann, CEO of ClearML, share insights on revolutionizing agriculture with AI. They reveal their staggering achievement of deploying thousands of models on Kubernetes clusters for tractors! The duo discusses the challenges and innovations in applying machine learning in farming, emphasizing the importance of automation in MLOps. They explore the role of real-time data processing and adaptive models, highlighting how this technology optimizes agricultural operations and boosts efficiency in the field.
AI Snips
Chapters
Transcript
Episode notes
GreenEye's MLOps Journey
- GreenEye initially lacked MLOps, relying on manual model training and deployment.
- Dockerizing and adopting Kubernetes revolutionized their workflow, enabling scaling and automation.
AI-Powered Precision Spraying
- Traditional crop spraying assumes the worst-case scenario, applying chemicals everywhere.
- GreenEye uses AI-powered sensors and cameras to spray only where needed, reducing chemical use.
MLOps Value in Iterative Processes
- Iterative processes, like model refinement, benefit from MLOps automation.
- This speeds up development and allows for quicker responses to changing scenarios.