Binary-Class Image Classification Model for Ultrasound Breast Cancer Classification 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 Ultrasound Breast Cancer Classification Dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The dataset contains 9,000 images of ultrasound images. The research team collected these images to investigate the machine learning model’s ability to distinguish benign and malignant breast cancer images. The research team also augmented the images by rotating and sharpening them to produce a sufficient amount of images.

ANALYSIS: The NASNetMobile model’s performance achieved an accuracy score of 99.42% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 91.00%.

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

Dataset ML Model: Binary classification with numerical features

Dataset Used: Ultrasound Breast Images for Breast Cancer

Dataset Reference: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer

One source of potential performance benchmarks: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer/code

The HTML formatted report can be found here on GitHub.

Binary-Class Image Classification Model for Ultrasound Breast Cancer Classification 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 Ultrasound Breast Cancer Classification Dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The dataset contains 9,000 images of ultrasound images. The research team collected these images to investigate the machine learning model’s ability to distinguish benign and malignant breast cancer images. The research team also augmented the images by rotating and sharpening them to produce a sufficient amount of images.

ANALYSIS: The ResNet50V2 model’s performance achieved an accuracy score of 98.97% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 95.56%.

CONCLUSION: In this iteration, the TensorFlow ResNet50V2 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Binary classification with numerical features

Dataset Used: Ultrasound Breast Images for Breast Cancer

Dataset Reference: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer

One source of potential performance benchmarks: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer/code

The HTML formatted report can be found here on GitHub.

Binary-Class Image Classification Model for Ultrasound Breast Cancer Classification 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 Ultrasound Breast Cancer Classification Dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The dataset contains 9,000 images of ultrasound images. The research team collected these images to investigate the machine learning model’s ability to distinguish benign and malignant breast cancer images. The research team also augmented the images by rotating and sharpening them to produce a sufficient amount of images.

ANALYSIS: The EfficientNetV2M model’s performance achieved an accuracy score of 98.82% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 97.00%.

CONCLUSION: In this iteration, the TensorFlow EfficientNetV2M CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Binary classification with numerical features

Dataset Used: Ultrasound Breast Images for Breast Cancer

Dataset Reference: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer

One source of potential performance benchmarks: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer/code

The HTML formatted report can be found here on GitHub.

Binary-Class Image Classification Model for Ultrasound Breast Cancer Classification 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 Ultrasound Breast Cancer Classification Dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The dataset contains 9,000 images of ultrasound images. The research team collected these images to investigate the machine learning model’s ability to distinguish benign and malignant breast cancer images. The research team also augmented the images by rotating and sharpening them to produce a sufficient amount of images.

ANALYSIS: The Xception model’s performance achieved an accuracy score of 99.57% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 98.33%.

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

Dataset ML Model: Binary classification with numerical features

Dataset Used: Ultrasound Breast Images for Breast Cancer

Dataset Reference: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer

One source of potential performance benchmarks: https://www.kaggle.com/datasets/vuppalaadithyasairam/ultrasound-breast-images-for-breast-cancer/code

The HTML formatted report can be found here on GitHub.

Michael Bungay Stanier on Do More Great Work, Part 7

In the book, Do More Great Work.: Stop the Busywork, and Start the Work that Matters, Michael Bungay Stanier shares his inspiration and techniques to help us do more work that matters.

These are some of my favorite takeaways from reading the book.

Map 6 What’s Broken

In this chapter, Michael talks about how we can use some pain points in our lives to inspire Great Work.

He recommends we take the following steps:

Take a look at the map with the concentric circles in the book. Start in the inner circle and think about what we would like to change the various elements within our lives.

Work through the circles and write down at least two things we would like to change within each domain.

Go back to the list and circle the five possible candidates for Great Work that we are most drawn to.

Somewhere in the list will likely be some possibilities for Great Work – a challenge with the appropriate scale for us.

Also, pay attention to the little things that get in our way but we have chosen to put up with. Either we choose to handle them as they come, or we feel that we cannot be bothered to change those things right now.

Over time, we stop noticing some of those little annoyances. Reducing such accepted irritants one by one is a beautiful way to chip away at the things obscuring our Great Work.

光明正大

(從我一個尊敬的作家,賽斯·高汀

公平往往只是在旁觀者的眼中。你認為什麼是公平可能取決於你在交易中的位置。輸家往往認為結果比贏家更不公平。

但是正大?

正大的問題是每個人都可以就這部分來達成一致。

如果某件事是光明正大的,那麼輸家可以與贏家意見一致,因為公平已不是相對的。

這秘訣很簡單:如果無論你支持什麼,計算看起來都一樣,那麼你就找到了該做的方法。結果應該是與方法無牽連。

Multi-Class Image Classification Model for Tomato Leaf Disease 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 Tomato Leaf Disease 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 20,000 images of tomato leaves with ten diseases and one healthy class. The research team collected these images to investigate the possibilities of developing a lightweight model that can predict tomato leaf disease on a mobile app.

ANALYSIS: The InceptionV3 model’s performance achieved an accuracy score of 97.54% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 96.75%.

CONCLUSION: In this iteration, the TensorFlow InceptionV3 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Tomato Leaves Dataset

Dataset Reference: https://www.kaggle.com/datasets/ashishmotwani/tomato

One source of potential performance benchmarks: https://www.kaggle.com/datasets/ashishmotwani/tomato/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Tomato Leaf Disease 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 Tomato Leaf Disease 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 20,000 images of tomato leaves with ten diseases and one healthy class. The research team collected these images to investigate the possibilities of developing a lightweight model that can predict tomato leaf disease on a mobile app.

ANALYSIS: The NASNetMobile model’s performance achieved an accuracy score of 97.49% after ten epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 84.33%.

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: Tomato Leaves Dataset

Dataset Reference: https://www.kaggle.com/datasets/ashishmotwani/tomato

One source of potential performance benchmarks: https://www.kaggle.com/datasets/ashishmotwani/tomato/code

The HTML formatted report can be found here on GitHub.