Multi-Class Image Classification Model for Shoes Footwear Types 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 Shoes Footwear Types 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 13,000 images of shoes in five classes. The training set contains 2,000 training images assigned to each class. The validation set contains 500 validation images assigned to each class. The test set has a random number of images assigned to each class.

ANALYSIS: The Xception model’s performance achieved an accuracy score of 88.16% after five epochs using the validation dataset. When we applied the model to the test dataset, the model achieved an accuracy score of 86.26%.

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

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Shoes Classification Dataset

Dataset Reference: https://www.kaggle.com/datasets/utkarshsaxenadn/shoes-classification-dataset-13k-images

One source of potential performance benchmarks: https://www.kaggle.com/datasets/utkarshsaxenadn/shoes-classification-dataset-13k-images/code

The HTML formatted report can be found here on GitHub.

Michael Bungay Stanier on Do More Great Work, Part 8

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 7 What’s Required

In this chapter, Michael talks about how we can balance the Great Work we would like to do and other competing forces that require our time and attention. Those competing forces usually come from the organizations where we work and have agendas and priorities outside our control.

He recommends we take the following steps:

Create a map with four quadrants. Label the X-axis with “They don’t care” on the left and “They care” on the right. Label the Y-axis with “I care” at the top and “I don’t care” at the bottom.

Next, we jot down all the work we do on a daily or weekly basis on a piece of paper. The more complete and specific we can be, the more useful this map will be. Figure out where our time goes.

Once we have a complete or comprehensive list, we can start plotting those tasks in the four boxes on the map.

In the top-right box, map all the work our organization wants us to do that is also meaningful. This is a sweet spot. Spend time here and seek out more work to do in this quadrant.

In the bottom-left box, list the work we do not care about and the organization does not either. We need to stop doing this work because they are pointless. If we must do this work, we must find a way to deliver the result at a minimally acceptable level with the least amount of time invested.

On the bottom-right corner, list the work we do not have a passion for but our organization expects it to be done. In the top-left box, put down the work we would like to do more but the organization does not value it. Working in these two quadrants requires us to exercise professional judgment and appropriate tactics.

使用您的門票

(從我一個尊敬的作家,賽斯·高汀

雖然我們很容易將我們的人生視為一個無限的遊樂,但事實並非如此。 它也可能不會最大化我們的影響或享受。

事實上,我們每個人能拿出來的門票的數量都是有限的。有限的時間、有限的機會、有限的金錢和其他資源。

所以今天的票要怎麼花?

Binary-Class Image Classification Model for Ultrasound Breast Cancer Classification 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 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 InceptionV3 model’s performance achieved an accuracy score of 99.33% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 97.56%.

CONCLUSION: In this iteration, the TensorFlow InceptionV3 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 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.