Multi-Class Image Classification Analytics Project Template Using TensorFlow Version 2

As I work on practicing and solving machine learning (ML) problems, I find myself repeating a set of steps and activities repeatedly.

Thanks to Dr. Jason Brownlee’s suggestions on creating a machine learning template, I have pulled together a project template that I use to experiment with modeling image classification problems using Python and the TensorFlow library.

Version 2 of the TensorFlow templates contain updated structures and code like the previous image classification TensorFlow templates. I designed the templates to address multi-class modeling exercises from beginning to end.

You will find the Python templates on the Analytics Project Templates page.

Binary Class Image Classification Analytics Project Template Using TensorFlow Version 2

As I work on practicing and solving machine learning (ML) problems, I find myself repeating a set of steps and activities repeatedly.

Thanks to Dr. Jason Brownlee’s suggestions on creating a machine learning template, I have pulled together a project template that I use to experiment with modeling image classification problems using Python and the TensorFlow library.

Version 2 of the TensorFlow templates contain updated structures and code like the previous image classification TensorFlow templates. I designed the templates to address binary class modeling exercises from beginning to end.

You will find the Python templates on the Analytics Project Templates page.

Binary Class Image Classification Deep Learning Model for Meat Quality Assessment Using TensorFlow Take 5

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 Meat Quality Assessment dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The research team collected the dataset to develop a meat quality assessment system based on deep learning. The published paper explains all of the experimental results, proving the usability of the dataset and model. This dataset contains fresh and spoiled red meat samples from a supermarket in Izmir, Turkey, for a university-industry collaboration project at the Izmir University of Economics.

For this modeling project, we will predict whether an image represents a fresh or spoiled meat case. In this iteration, we will construct a CNN model based on the DenseNet201 architecture to make predictions.

ANALYSIS: In this iteration, the DenseNet201 model’s performance achieved an accuracy score of 99.80% after 10 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 94.97%.

CONCLUSION: In this iteration, the DenseNet201-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Meat Quality Assessment

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://www.kaggle.com/crowww/meat-quality-assessment-based-on-deep-learning

One potential source of performance benchmarks: https://ieeexplore.ieee.org/abstract/document/8946388

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for Meat Quality Assessment Using TensorFlow Take 4

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 Meat Quality Assessment dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The research team collected the dataset to develop a meat quality assessment system based on deep learning. The published paper explains all of the experimental results, proving the usability of the dataset and model. This dataset contains fresh and spoiled red meat samples from a supermarket in Izmir, Turkey, for a university-industry collaboration project at the Izmir University of Economics.

For this modeling project, we will predict whether an image represents a fresh or spoiled meat case. In this iteration, we will construct a CNN model based on the EfficientNetB5 architecture to make predictions.

ANALYSIS: In this iteration, the EfficientNetB5 model’s performance achieved an accuracy score of 94.86% after 10 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 98.68%.

CONCLUSION: In this iteration, the EfficientNetB5-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Meat Quality Assessment

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://www.kaggle.com/crowww/meat-quality-assessment-based-on-deep-learning

One potential source of performance benchmarks: https://ieeexplore.ieee.org/abstract/document/8946388

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for Meat Quality Assessment 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 Meat Quality Assessment dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The research team collected the dataset to develop a meat quality assessment system based on deep learning. The published paper explains all of the experimental results, proving the usability of the dataset and model. This dataset contains fresh and spoiled red meat samples from a supermarket in Izmir, Turkey, for a university-industry collaboration project at the Izmir University of Economics.

For this modeling project, we will predict whether an image represents a fresh or spoiled meat case. In this iteration, we will construct a CNN model based on the VGG19 architecture to make predictions.

ANALYSIS: In this iteration, the VGG19 model’s performance achieved an accuracy score of 92.36% after 15 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 100.00%.

CONCLUSION: In this iteration, the VGG19-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Meat Quality Assessment

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://www.kaggle.com/crowww/meat-quality-assessment-based-on-deep-learning

One potential source of performance benchmarks: https://ieeexplore.ieee.org/abstract/document/8946388

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for Meat Quality Assessment Using TensorFlow Take 2

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 Meat Quality Assessment dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The research team collected the dataset to develop a meat quality assessment system based on deep learning. The published paper explains all of the experimental results, proving the usability of the dataset and model. This dataset contains fresh and spoiled red meat samples from a supermarket in Izmir, Turkey, for a university-industry collaboration project at the Izmir University of Economics.

For this modeling project, we will predict whether an image represents a fresh or spoiled meat case. In this iteration, we will construct a CNN model based on the ResNet152V2 architecture to make predictions.

ANALYSIS: In this iteration, the ResNet152V2 model’s performance achieved an accuracy score of 98.88% after 15 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 88.10%.

CONCLUSION: In this iteration, the ResNet152V2-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Meat Quality Assessment

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://www.kaggle.com/crowww/meat-quality-assessment-based-on-deep-learning

One potential source of performance benchmarks: https://ieeexplore.ieee.org/abstract/document/8946388

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for Meat Quality Assessment 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 Meat Quality Assessment dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The research team collected the dataset to develop a meat quality assessment system based on deep learning. The published paper explains all of the experimental results, proving the usability of the dataset and model. This dataset contains fresh and spoiled red meat samples from a supermarket in Izmir, Turkey, for a university-industry collaboration project at the Izmir University of Economics.

For this modeling project, we will predict whether an image represents a fresh or spoiled meat case. In this iteration, we will construct a CNN model based on the InceptionV3 architecture to make predictions.

ANALYSIS: In this iteration, the InceptionV3 model’s performance achieved an accuracy score of 99.80% after 15 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 92.86%.

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: Meat Quality Assessment

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://www.kaggle.com/crowww/meat-quality-assessment-based-on-deep-learning

One potential source of performance benchmarks: https://ieeexplore.ieee.org/abstract/document/8946388

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Deep Learning Model for ISIC Challenge 2017 Using TensorFlow Take 4

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 ISIC Challenge 2017 dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The International Skin Imaging Collaboration (ISIC) is an international effort to improve melanoma diagnosis, sponsored by the International Society for Digital Imaging of the Skin (ISDIS). The ISIC Archive contains the most extensive publicly available collection of quality-controlled dermoscopic images of skin lesions. Since 2016, ISIC has sponsored annual challenges for the computer science community associated with leading computer vision conferences.

For this modeling project, we will predict whether an image represents a melanoma, nevus, or seborrheic keratosis case. In this iteration, we will construct a CNN model based on the EfficientNetB7 architecture to make predictions.

ANALYSIS: In this iteration, the EfficientNetB7 model’s performance achieved an accuracy score of 87.50% after 15 epochs using the training dataset. The same model processed the validation dataset with an accuracy rate of 73.33%. Finally, the final model processed the test dataset with an accuracy score of 68.50%.

CONCLUSION: In this iteration, the EfficientNetB7-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: ISIC Challenge 2017 Dataset

Dataset ML Model: Multi-Class classification with numerical attributes

Dataset Reference: https://challenge.isic-archive.com/data

One potential source of performance benchmarks: https://challenge.isic-archive.com/leaderboards/2017

The HTML formatted report can be found here on GitHub.