Cardz is my take on playing card localization and classification in a scence with multiple cards.
The model consists of an UNet trained with random card ensembles and their segmentation masks. The trained models can be found in results.
This repository contains a notebook explaining the biggest model and analysing its perfomance using Captum.
Here is a basic table of contents:
- Classifier: Training the model
- Captum: Evaluating the model quality using Captum