Multi-Class Image Classification Deep Learning Model for Large Scale Fish Images Using TensorFlow Take 1

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 Large Scale Fish Images dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: This dataset contains nine different seafood types collected from a supermarket in Izmir, Turkey, for a university-industry collaboration project at Izmir University of Economics, and this work was published in ASYU 2020. For each class, there are 1000 augmented images and their pair-wise augmented ground truths.

In this Take1 iteration, we will construct a CNN model based on the InceptionV3 architecture to predict the leaf’s health state based on the available images.

ANALYSIS: In this Take1 iteration, the InceptionV3 model’s performance achieved an accuracy score of 99.65% after ten epochs using the training dataset. The same model processed the validation dataset with an accuracy score of 93.83%.

CONCLUSION: In this iteration, the InceptionV3-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: A Large-Scale Dataset for Fish Segmentation and Classification

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

Dataset Reference: Ulucan, Oguzhan and Karakaya, Diclehan and Turkan, Mehmet (2020), “A Large-Scale Dataset for Fish Segmentation and Classification,” 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), IEEE (

One potential source of performance benchmarks:

The HTML formatted report can be found here on GitHub.