KenningΒΆ
- Introduction
- Kenning
- Deep Learning deployment stack
- Defining optimization pipelines in Kenning
- Using Kenning via command line arguments
- Kenning gallery of use cases
- Generating anomaly detection models for the MAX32690 Evaluation Kit with AutoML
- Anomaly detection model training and deployment on the MAX32690 Evaluation Kit
- Displaying information about available classes
- Evaluating models on hardware using Kenning Zephyr Runtime
- Visualizing Kenning data flows with Pipeline Manager
- Bare-metal IREE runtime simulated using Renode
- Structured pruning for PyTorch models
- Model quantization and compilation using TFLite and TVM
- Unstructured Pruning of TensorFlow Models
- Optimizing and comparing instance segmentation models
- Kenning environment variables
- Kenning measurements
- Choosing optimal optimization pipeline
- Sample autogenerated report
- Sample AutoML report
- Comparison of workspace.automl-results.1234_3_5.0.measurements.json, workspace.automl-results.1234_12_5.0.measurements.json, workspace.automl-results.1234_21_5.0.measurements.json, workspace.automl-results.1234_29_1.6666666666666665.measurements.json and workspace.automl-results.1234_29_5.0.measurements.json
- AutoML statistics
- Classification comparison
- Inference comparison
- Renode performance measurements
- Creating applications with Kenning
- Developing Kenning blocks
- Kenning resources
- Kenning protocols
- Kenning platforms
- Kenning API
Last update:
2025-10-07