Multi-Class Image Classification Model for Animal Images Version 1 Using TensorFlow Take 3

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 Animal Image Classification Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains over 11,000 images of five different animals. The training set contains 1,500 training images assigned to each class. The validation set contains 500 validation images assigned to each class. Finally, the test set has a random number of pictures assigned to each class.

ANALYSIS: The NASNetMobile model’s performance achieved an accuracy score of 96.84% after ten epochs using the validation dataset. When we applied the model to the test dataset, the model achieved an accuracy score of 96.01%.

CONCLUSION: In this iteration, the TensorFlow NASNetMobile CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Animal Image Classification Dataset

Dataset Reference:

One source of potential performance benchmarks:

The HTML formatted report can be found here on GitHub.