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

INTRODUCTION: The dataset owner collected multi-categorical images of Indian delicacies for training computer vision models. The dataset owner also resized the photos to a 300-by-300 resolution to maintain size consistency.

ANALYSIS: The model’s performance achieved an accuracy score of 33.47% after 20 epochs using a validation dataset with 15% of total images. After tuning the learning rate, we improved the accuracy rate to 51.91% using the same validation dataset.

CONCLUSION: In this iteration, the TensorFlow ResNet152V2 CNN model appeared to have limited effectiveness in modeling this dataset.

Dataset Used: Massive Indian Food Dataset

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

Dataset Reference: https://www.kaggle.com/anshulmehtakaggl/themassiveindianfooddataset

One potential source of performance benchmarks: https://www.kaggle.com/anshulmehtakaggl/themassiveindianfooddataset/code

The HTML formatted report can be found here on GitHub.

• Blog