Leverage Power of Machine Learning with ONNX
summary
Shows converting a small ML.NET linear regression trained on a 13‑row salary CSV into an ONNX file, then running inference from Python with ONNX Runtime to prove portability and performance. Covers ML.NET → ONNX export, visualizing graphs with Netron, using the ONNX Runtime (CPU/GPU/DirectML) and deploying to browser with ONNX.js. Cites ONNX ecosystem size (~11,000 GitHub stars, ~2,000 forks/PRs, ~200 contributors) and demonstrates the conversion and end‑to‑end inferencing working.
AI-written summary · about
chapters (11)
- 0:00ONNX introduction
- 0:54What is ONNX
- 3:42When to use ONNX
- 7:56Creating ONNX models
- 14:48End-to-end ML with ONNX
- 15:56Deploying ONNX models
- 20:55ONNX at the edge
- 23:27ONNX Runtime acceleration
- 27:45Demo: ML.NET to ONNX
- 37:53ONNX benefits
- 39:41Closing
related talks
45mLeverage Power of Machine Learning with ONNX
05mONNX Runtime
45mMaking Machine Learning Applications Fast and Simple with...
30mScalable ML acceleration with ONNX Runtime
51mMaking neural networks run in browser with ONNX
30mThe Evolution of ONNX: Driving Interoperability in AI...
33mWhat on earth is ONNX and ONNXRUNTIME
33mMachine Learning in the Browser: Fast Iteration with ONNX & WebAssembly