mrob937/2025-24679-image-autogluon-predictor

Model Card for mrob937/2024-24679-image-autogluon-predictor

Model Description

This is an AutoGluon Tabular AutoML implementation on a tabular dataset recording images of playing cards where the target variables indicate whether or not the card is a face or number card.

• Model developed by: Myles Robinson
• Model type: AutoGluon MultiModalPredictor

Model Sources [optional]

• Dataset: aedupuga/cards-image-dataset

Direct Use

• This model was intended to practice automl implementation on an image dataset

Bias, Risks, and Limitations

• Small data size.
• Personal preference of the dataset creator in classification.

Training Data:

The model was trained on the augmented split of the "aedupuga/cards-image-dataset" dataset. The data includes images of playing cards where the target variable indicates whether the given card is a face card or not.

Evaluation Data:

The model achieved an accuracy of 1.00 and a weighted F1 score of 1.00 on the original dataset.

Model Card Contact

Myles Robinson (Carnegie Mellon Univerity)- [email protected]