How industrial-edge/ai-sdk-tutorials works
This repository is a collection of AI SDK tutorials and guides, not the SDK implementation itself. Its principal user workflow is to prepare data, train a model, package it as an inference pipeline, test the package locally, and optionally generate an AI@Edge pipeline. The graph includes sampled inference examples and README-documented workflow capabilities; links to unsampled tutorial stages are documented rather than inferred from code.
Main entry points: e2e-tutorials Pipeline Packaging · inference.py State Inference · entrypoint.py Image Entry Point · entrypoint_tf.py TensorFlow Entry
Components 20
ML Workflow
- Model Training
e2e-tutorials - Pipeline Packaging
e2e-tutorials - Local Testing
e2e-tutorials - Edge Pipeline
e2e-tutorials
Inference Examples
- Image Entry Point
e2e-tutorials/image_classification/entrypoint.py - TFLite Classifier
e2e-tutorials/image_classification/src/vision_classifier.py - TensorFlow Entry
e2e-tutorials/image_classification/entrypoint_tf.py - TensorFlow Classifier
e2e-tutorials/image_classification/src/vision_classifier_tf.py - State Entry Point
e2e-tutorials/state_identifier/entrypoint.py - State Inference
e2e-tutorials/state_identifier/src/si/inference.py - Time-Series Pipeline
e2e-tutorials/state_identifier/src/si/pipeline.py - Detection Postprocess
e2e-tutorials/object_detection/src/postprocessing/postprocessing.py - Detection Drawing
e2e-tutorials/object_detection/src/image_utils.py - Detection Preprocess
e2e-tutorials/object_detection/src/preprocessing/preprocessing.py - Image Segmentation
e2e-tutorials/segmentation/src/segmentation.py - Batch State Example
e2e-tutorials/batch_state_identifier/src/si/pipeline.py - Soft Sensor Example
e2e-tutorials/soft_sensor/src/inference/entrypoint.py
Packaging Guides
- Packaging How-tos
howto-guides - Runnable How-to Notebooks
howto-notebooks
Other components
- Tutorial User
Connections 11
- Tutorial User → Model Training: prepares data
README.md - Model Training → Pipeline Packaging: packages model
README.md - Pipeline Packaging → Local Testing: tests package
README.md - Pipeline Packaging → Edge Pipeline: generates pipeline
README.md - Tutorial User → Packaging How-tos: consults
README.md - Tutorial User → Runnable How-to Notebooks: runs examples
README.md - Image Entry Point → TFLite Classifier: calls classifier
e2e-tutorials/image_classification/entrypoint.py - TensorFlow Entry → TensorFlow Classifier: calls classifier
e2e-tutorials/image_classification/entrypoint_tf.py - State Entry Point → State Inference: delegates inference
e2e-tutorials/state_identifier/entrypoint.py - State Inference → Time-Series Pipeline: transforms window
- Detection Postprocess → Detection Drawing: draws predictions
e2e-tutorials/object_detection/src/postprocessing/postprocessing.py