Skip to main content

AI REGIO Quality control on production lines with Computer Vision and TinyML

This repository includes a jupyter notebook that presents a complete pipeline for:

EDA on image data
Data preparation and augmentation
Deep learning (CNN) models development for image classification with TensorFlow
Models evaluation
Model interpretation predictions with LIME
Transformation to TFLite format to allow their usage in embedded devices
Post-training quantization
Quantization aware training
Overall evaluation
Complete explanations of the above are available in the notebook, which is also available in PDF format.

Moreover, there is a python script that allows the real-time usage of the developed models on video streams.

Part of the development of this asset was supported by the AI REGIO project, which has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreements No 952003 (AI REGIO).