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 Grapevine Leaves Image Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.
INTRODUCTION: The main product of grapevines is grapes that are consumed fresh or processed. In addition, grapevine leaves are harvested once a year as a by-product. Therefore, the species of grapevine leaves are essential factors in price and taste. The research team deployed deep learning-based classification models in this study to identify grapevine leaves. For this study, 500 images of vine leaves make up the dataset.
ANALYSIS: The EfficientNetV2L model’s performance achieved an accuracy score of 90.89% after 30 epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 90.00%.
CONCLUSION: In this iteration, the TensorFlow EfficientNetV2L CNN model appeared suitable for modeling this dataset.
Dataset ML Model: Multi-Class classification with numerical features
Dataset Used: Grapevine Leaves Image Dataset
Dataset Reference: https://www.muratkoklu.com/datasets/
One source of potential performance benchmarks: https://doi.org/10.1016/j.measurement.2021.110425
The HTML formatted report can be found here on GitHub.