Multi-Class Image Classification Model for 7000 Labeled Pokémon 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 7000 Labeled Pokémon dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset owner worked on a Pokémon classification project and made the dataset available on Kaggle. The dataset includes 150 Pokémon’s with 25 to 50 images for each Pokémon. Unfortunately, most images have low resolution, so we should be mindful of the results that we can obtain from this dataset.

ANALYSIS: The model’s performance achieved an accuracy score of 57.70% after 50 epochs using a validation dataset with 15% of total images. After tuning the learning rate, we could not improve the accuracy rate using the same validation dataset.

CONCLUSION: In this iteration, the TensorFlow InceptionV3 CNN model appeared to have limited effectiveness in modeling this dataset.

Dataset Used: 7000 Labeled Pokémon

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

Dataset Reference: https://www.kaggle.com/lantian773030/pokemonclassification

One potential source of performance benchmarks: https://www.kaggle.com/lantian773030/pokemonclassification/code

The HTML formatted report can be found here on GitHub.

Seth Godin on Survival Is Not Enough, Part 10

In his book, Survival Is Not Enough: Why Smart Companies Abandon Worry and Embrace Change, Seth Godin discusses how innovative organizations and individuals can apply prudent strategies in adapting and positioning themselves for the constant changes. [https://smile.amazon.com/Survival-Not-Enough-Companies-Abandon-ebook/dp/B002XQAB08/]

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

Chapter 10, Tactics for Accelerating Evolution

In this chapter, Seth discusses the tactics we can use to help our organization and people zoom and evolve. He offers the following observations and recommendations for us to think about:

  • Adding a charrette element to our projects can be productive. The power of the charrette is that when there is a hard stop on a project, people figure out how to prioritize their objections. In the meantime, we are still managing the process, but we need to have established an environment in which people can create without fear.
  • We need to start introducing new ideas regularly. This move can dramatically increase the pace and impact of memetic change within our organizations by creating artificial markers. Creating these opportunities and leveraging them is a positive step toward pushing the organization to zoom.
  • One approach for consistently coming up with new ideas is to have alternate teams that work on the project. The two groups can take advantage of the other team’s gems while learning from the other team’s mistakes. In addition, by alternating the teams, the internal competition and overlapping development cycles could accelerate the design and feedback process on all projects.
  • We should embrace the fact that better often beats perfect. Unfortunately, there is no such thing as the perfect solution in a competitive marketplace. By the time we develop perfect, our competition will probably have changed the landscape so much that our product will not even be good anymore.
  • When we embrace good instead of perfect, we open ourselves up to receiving feedback. The feedback can help us evolve our products and make them good enough where perfect might not matter.

In summary:

“Once a company understands the need to zoom, it can start to build tools that increase its ability to adapt to a changing environment.”

最佳行為

(從我一個尊敬的作家,賽斯·高汀

如果我們對某種情況不熟悉時,或者感到不確定,我們會特別注意。 我們會仔細研究其他人的感受、文化規範是什麼,以及我們正在尋求產生什麼樣的影響。

另一方面,有時我們無法保持最佳的行為。這時候是描述衝動自私的另一種方式。

令人驚訝的是,保持最佳行為並不一定會讓事情進展得更順利。 不,對於我們中的許多人來說,令人驚訝的是它實際上能讓我們的體驗變得更好,而不僅僅只是對其他人。

Multi-Class Image Classification Model for Vegetable Image Dataset 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 Vegetable Image Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: From vegetable production to delivery, common steps such as picking and sorting vegetables often occur manually. The research team wanted to improve the operation by developing a deep neural network model to detect and classify vegetables. That model can be implemented within different types of devices and can also solve other problems related to identifying vegetables, like labeling the vegetables automatically without any need for human work.

The initial experiment looked at 15 types of common vegetables found throughout the world. The vegetables chosen for the experimentation include bean, bitter gourd, bottle gourd, brinjal, broccoli, cabbage, capsicum, carrot, cauliflower, cucumber, papaya, potato, pumpkin, radish, and tomato. A total of 21000 images from 15 classes are used, where each class contains 1400 images of size 224×224 and in JPG format. The dataset split 70% for training, 15% for validation, and 15% for testing purposes.

ANALYSIS: The performance of the baseline model achieved an accuracy score of 85.77% after ten epochs using the validation datasets. After tuning the hyperparameters, the best model processed the validation dataset with an accuracy score of 97.77%. Furthermore, the final model processed the test dataset with an accuracy measurement of 86.67%.

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

Dataset Used: Vegetable Image Dataset

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

Dataset Reference: https://www.kaggle.com/misrakahmed/vegetable-image-dataset

One potential source of performance benchmarks: https://www.kaggle.com/misrakahmed/vegetable-image-dataset/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Vegetable Image Dataset 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 Vegetable Image Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: From vegetable production to delivery, common steps such as picking and sorting vegetables often occur manually. The research team wanted to improve the operation by developing a deep neural network model to detect and classify vegetables. That model can be implemented within different devices and can also solve other problems related to identifying vegetables, like labeling the vegetables automatically without any need for human work.

The initial experiment looked at 15 common vegetables found throughout the world. The vegetables chosen for the experimentation include bean, bitter gourd, bottle gourd, brinjal, broccoli, cabbage, capsicum, carrot, cauliflower, cucumber, papaya, potato, pumpkin, radish, and tomato. A total of 21000 images from 15 classes are used, where each class contains 1400 images of size 224×224 and in JPG format. The dataset split 70% for training, 15% for validation, and 15% for testing purposes.

ANALYSIS: The performance of the baseline model achieved an accuracy score of 95.53% after ten epochs using the validation datasets. After tuning the hyperparameters, the best model processed the validation dataset with an accuracy score of 99.70%. Furthermore, the final model processed the test dataset with an accuracy measurement of 98.67%.

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

Dataset Used: Vegetable Image Dataset

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

Dataset Reference: https://www.kaggle.com/misrakahmed/vegetable-image-dataset

One potential source of performance benchmarks: https://www.kaggle.com/misrakahmed/vegetable-image-dataset/code

The HTML formatted report can be found here on GitHub.

Univariate Time Series LSTM Modeling Template Using TensorFlow Version 1

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 can be used to support time series analysis using the TensorFlow framework and Python.

Version 1 of the TensorFlow LSTM time series template replicates Dr. Brownlee’s blog post “Deep Learning Models for Univariate Time Series Forecasting”. I plan to build a script for modeling future projects by adapting the example workflow presented in the blog.

You will find the Python time series template on the Analytics Project Templates page.

Multi-Class Image Classification Model for Vegetable Image Dataset Using TensorFlow Take 2

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery. [https://machinelearningmastery.com/]

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

INTRODUCTION: From vegetable production to delivery, common steps such as picking and sorting vegetables often occur manually. The research team wanted to improve the operation by developing a deep neural network model to detect and classify vegetables. That model can be implemented within different types of devices and can also solve other problems related to identifying vegetables, like labeling the vegetables automatically without any need for human work.

The initial experiment looked at 15 types of common vegetables found throughout the world. The vegetables chosen for the experimentation include bean, bitter gourd, bottle gourd, brinjal, broccoli, cabbage, capsicum, carrot, cauliflower, cucumber, papaya, potato, pumpkin, radish, and tomato. A total of 21000 images from 15 classes are used, where each class contains 1400 images of size 224×224 and in JPG format. The dataset split 70% for training, 15% for validation, and 15% for testing purposes.

ANALYSIS: The performance of the baseline model achieved an accuracy score of 55.77% after ten epochs using the validation datasets. After tuning the hyperparameters, the best model processed the validation dataset with an accuracy score of 99.67%. Furthermore, the final model processed the test dataset with an accuracy measurement of 92.60%.

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

Dataset Used: Vegetable Image Dataset

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

Dataset Reference: https://www.kaggle.com/misrakahmed/vegetable-image-dataset

One potential source of performance benchmarks: https://www.kaggle.com/misrakahmed/vegetable-image-dataset/code

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Model for Vegetable Image Dataset 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 Vegetable Image Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: From vegetable production to delivery, common steps such as picking and sorting vegetables often occur manually. The research team wanted to improve the operation by developing a deep neural network model to detect and classify vegetables. That model can be implemented within different types of devices and can also solve other problems related to identifying vegetables, like labeling the vegetables automatically without any need for human work.

The initial experiment looked at 15 types of common vegetables found throughout the world. The vegetables chosen for the experimentation include bean, bitter gourd, bottle gourd, brinjal, broccoli, cabbage, capsicum, carrot, cauliflower, cucumber, papaya, potato, pumpkin, radish, and tomato. A total of 21000 images from 15 classes are used, where each class contains 1400 images of size 224×224 and in JPG format. The dataset split 70% for training, 15% for validation, and 15% for testing purposes.

ANALYSIS: The performance of the baseline model achieved an accuracy score of 91.93% after ten epochs using the validation datasets. After tuning the hyperparameters, the best model processed the validation dataset with an accuracy score of 99.73%. Furthermore, the final model processed the test dataset with an accuracy measurement of 99.19%.

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

Dataset Used: Vegetable Image Dataset

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

Dataset Reference: https://www.kaggle.com/misrakahmed/vegetable-image-dataset

One potential source of performance benchmarks: https://www.kaggle.com/misrakahmed/vegetable-image-dataset/code

The HTML formatted report can be found here on GitHub.