Multi-Class Image Classification Model for Deepmind 3D Shapes Using TensorFlow

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 Deepmind 3D Shapes dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: 3dshapes is a dataset of 3D shapes procedurally generated from six independent latent factors. These factors are floor color, wall color, object color, scale, shape, and orientation. By varying just one latent factor at a time, the researchers were able to generate 480000 images for the dataset.

In this Take1 iteration, we will construct a simple three-layer CNN model to predict the shape in each image.

ANALYSIS: The performance of the baseline model achieved an accuracy score of 99.91% after five epochs using the training dataset. The same model processed the validation dataset with an accuracy score of 99.95%.

CONCLUSION: In this iteration, the TensorFlow CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Deepmind 3D Shapes dataset

Dataset ML Model: Multi-class image classification with numerical attributes

Dataset Reference:

One potential source of performance benchmarks:

The HTML formatted report can be found here on GitHub.