Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.
SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Mango Varieties Classification dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.
INTRODUCTION: This dataset contains 1,600 images of eight varieties of Pakistani mangoes. The research team performed experiments on the dataset to create an automated classification and grading system. The system classifies the harvested mangoes for farmers to deliver high-quality mangoes for export with high accuracy.
ANALYSIS: The DenseNet201 model’s performance achieved an accuracy score of 99.79% after 20 epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 96.88%.
CONCLUSION: In this iteration, the TensorFlow DenseNet201 CNN model appeared suitable for modeling this dataset.
Dataset ML Model: Multi-Class classification with numerical features
Dataset Used: Mango Varieties Classification and Grading, Rizwan Iqbal, Hafiz Muhammad; Hakim, Ayesha (2021), “Mango Variety and Grading Dataset,” Mendeley Data, V1, DOI: 10.17632/5mc3s86982.1
One source of potential performance benchmarks: https://www.kaggle.com/datasets/saurabhshahane/mango-varieties-classification/code
The HTML formatted report can be found here on GitHub.