Multi-Class Image Classification Deep Learning Model for Kaggle 275 Bird Species Using TensorFlow Take 6

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 Kaggle 275 Bird Species dataset is a multi-class classification situation where we attempt to predict one of several (for this dataset 275) possible outcomes.

INTRODUCTION: This dataset contains 275 bird species with 39364 training images, 1375 test images (5 per species), and 1375 validation images (5 per species. All images have a resolution of 224 X 224 X 3 color images in the jpg format. Each dataset includes 275 subdirectories, one for each bird species.

From iteration Take1, we constructed a simple three-layer CNN model to predict the species for the image.

From iteration Take2, we constructed a CNN model based on the InceptionV3 architecture to predict the species for the image.

From iteration Take3, we constructed a CNN model based on the VGG19 architecture to predict the species for the image.

From iteration Take4, we constructed a CNN model based on the ResNet152V2 architecture to predict the species for the image.

From iteration Take5, we will construct a CNN model based on the MobileNetV3Small architecture to predict the species for the image.

In this Take6 iteration, we will construct a CNN model based on the MobileNetV3Large architecture to predict the species for the image.

ANALYSIS: From iteration Take1, the simple three-layer CNN model’s performance achieved an accuracy score of 68.87% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 69.24%.

From iteration Take2, the InceptionV3 model’s performance achieved an accuracy score of 96.51% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.53%.

From iteration Take3, the VGG19 model’s performance achieved an accuracy score of 91.27% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 94.84%.

From iteration Take4, the ResNet152V2 model’s performance achieved an accuracy score of 97.96% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.60%.

From iteration Take5, the MobileNetV3Small model’s performance achieved an accuracy score of 94.33% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 95.85%.

In this Take6 iteration, the MobileNetV3Large model’s performance achieved an accuracy score of 96.44% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.60%.

CONCLUSION: In this iteration, the MobileNetV3Large-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Kaggle 275 Bird Species dataset

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

Dataset Reference: https://www.kaggle.com/gpiosenka/100-bird-species

One potential source of performance benchmarks: https://www.kaggle.com/gpiosenka/100-bird-species

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Deep Learning Model for Kaggle 275 Bird Species 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 Kaggle 275 Bird Species dataset is a multi-class classification situation where we attempt to predict one of several (for this dataset 275) possible outcomes.

INTRODUCTION: This dataset contains 275 bird species with 39364 training images, 1375 test images (5 per species), and 1375 validation images (5 per species. All images have a resolution of 224 X 224 X 3 color images in the jpg format. Each dataset includes 275 subdirectories, one for each bird species.

From iteration Take1, we constructed a simple three-layer CNN model to predict the species for the image.

From iteration Take2, we constructed a CNN model based on the InceptionV3 architecture to predict the species for the image.

From iteration Take3, we constructed a CNN model based on the VGG19 architecture to predict the species for the image.

From iteration Take4, we constructed a CNN model based on the ResNet152V2 architecture to predict the species for the image.

In this Take5 iteration, we will construct a CNN model based on the MobileNetV3Small architecture to predict the species for the image.

ANALYSIS: From iteration Take1, the simple three-layer CNN model’s performance achieved an accuracy score of 68.87% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 69.24%.

From iteration Take2, the InceptionV3 model’s performance achieved an accuracy score of 96.51% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.53%.

From iteration Take3, the VGG19 model’s performance achieved an accuracy score of 91.27% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 94.84%.

From iteration Take4, the ResNet152V2 model’s performance achieved an accuracy score of 97.96% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.60%.

In this Take5 iteration, the MobileNetV3Small model’s performance achieved an accuracy score of 94.33% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 95.85%.

CONCLUSION: In this iteration, the MobileNetV3Small-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: Kaggle 275 Bird Species dataset

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

Dataset Reference: https://www.kaggle.com/gpiosenka/100-bird-species

One potential source of performance benchmarks: https://www.kaggle.com/gpiosenka/100-bird-species

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Deep Learning Model for Kaggle 275 Bird Species 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 Kaggle 275 Bird Species dataset is a multi-class classification situation where we attempt to predict one of several (for this dataset 275) possible outcomes.

INTRODUCTION: This dataset contains 275 bird species with 39364 training images, 1375 test images (5 per species), and 1375 validation images (5 per species. All images have a resolution of 224 X 224 X 3 color images in the jpg format. Each dataset includes 275 subdirectories, one for each bird species.

From iteration Take1, we constructed a simple three-layer CNN model to predict the species for the image.

From iteration Take2, we constructed a CNN model based on the InceptionV3 architecture to predict the species for the image.

From iteration Take3, we constructed a CNN model based on the VGG19 architecture to predict the species for the image.

In this Take4 iteration, we will construct a CNN model based on the ResNet152V2 architecture to predict the species for the image.

ANALYSIS: From iteration Take1, the simple three-layer CNN model’s performance achieved an accuracy score of 68.87% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 69.24%.

From iteration Take2, the InceptionV3 model’s performance achieved an accuracy score of 96.51% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.53%.

From iteration Take3, the VGG19 model’s performance achieved an accuracy score of 91.27% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 94.84%.

In this Take4 iteration, the ResNet152V2 model’s performance achieved an accuracy score of 97.96% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.60%.

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: Kaggle 275 Bird Species dataset

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

Dataset Reference: https://www.kaggle.com/gpiosenka/100-bird-species

One potential source of performance benchmarks: https://www.kaggle.com/gpiosenka/100-bird-species

The HTML formatted report can be found here on GitHub.

Charlie Gilkey on Start Finishing, Part 4

In his book, Start Finishing: How to go from idea to done, Charlie Gilkey discusses how we can follow a nine-step method to convert an idea into a project and get the project done via a reality-based schedule.

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

Chapter 4, Convert Your Idea into a Project

In this chapter, Charlie discusses the steps to convert our chosen idea into a project. He offers the following views for us to think about:

  • A SMART goal is:
    • Simple: A simple goal is not necessarily an easy thing to do, but a goal is simple when we can look at it without wondering.
    • Meaningful: A goal is meaningful when we understand the importance of completing that goal.
    • Actionable: A goal is actionable when it is immediately clear what we need to do to accomplish the goal.
    • Realistic: A goal is realistic when we know we can achieve it with the available resources.
    • Trackable: A goal is trackable when it is apparent to us what progress means, either quantitatively or qualitatively.
  • There are three levels of success:
    • Small: A string of small successes done with coherence and intention can still lead to greater success down the road.
    • Moderate: Moderate success is the highest state we can achieve with just our own effort, resources, and advantages.
    • Epic: Epic success always requires us to build a team to help us achieve it.
    • Each level of success requires a corresponding amount of effort and focus, and we cannot do everything at the epic level.
  • Our success pack consists of four groups of people: guides, peers, supporters, and beneficiaries.
  • Steps for leveraging the success pack to go from idea to action:
    • List the three to five people who are a part of each group.
    • For each person, brainstorm at least three specific ways they can help us or we can help them.
    • Determine the frequency of communication that would be most supportive of the project.
    • Let each person know they are a part of our success pack.
    • Proactively communicate with and show our work per the agreed-upon communication frequency.
  • If a project does not have start and completion dates, it is not likely that it will get done.

Multi-Class Image Classification Deep Learning Model for Kaggle 275 Bird Species 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 Kaggle 275 Bird Species dataset is a multi-class classification situation where we attempt to predict one of several (for this dataset 275) possible outcomes.

INTRODUCTION: This dataset contains 275 bird species with 39364 training images, 1375 test images (5 per species), and 1375 validation images (5 per species. All images have a resolution of 224 X 224 X 3 color images in the jpg format. Each dataset includes 275 subdirectories, one for each bird species.

From iteration Take1, we constructed a simple three-layer CNN model to predict the species for the image.

From iteration Take2, we constructed a CNN model based on the InceptionV3 architecture to predict the species for the image.

In this Take3 iteration, we will construct a CNN model based on the VGG19 architecture to predict the species for the image.

ANALYSIS: From iteration Take1, the simple three-layer CNN model’s performance achieved an accuracy score of 68.87% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 69.24%.

From iteration Take2, the InceptionV3 model’s performance achieved an accuracy score of 96.51% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.53%.

In this Take3 iteration, the VGG19 model’s performance achieved an accuracy score of 91.27% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 94.84%.

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: Kaggle 275 Bird Species dataset

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

Dataset Reference: https://www.kaggle.com/gpiosenka/100-bird-species

One potential source of performance benchmarks: https://www.kaggle.com/gpiosenka/100-bird-species

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Deep Learning Model for Kaggle 275 Bird Species 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 Kaggle 275 Bird Species dataset is a multi-class classification situation where we attempt to predict one of several (for this dataset 275) possible outcomes.

INTRODUCTION: This dataset contains 275 bird species with 39364 training images, 1375 test images (5 per species), and 1375 validation images (5 per species. All images have a resolution of 224 X 224 X 3 color images in the jpg format. Each dataset includes 275 subdirectories, one for each bird species.

From iteration Take1, we constructed a simple three-layer CNN model to predict the species for the image.

In this Take2 iteration, we will construct a CNN model based on the InceptionV3 architecture to predict the species for the image.

ANALYSIS: From iteration Take1, the simple three-layer CNN model’s performance achieved an accuracy score of 68.87% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 69.24%.

In this Take2 iteration, the InceptionV3 model’s performance achieved an accuracy score of 96.51% after 20 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 97.53%.

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: Kaggle 275 Bird Species dataset

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

Dataset Reference: https://www.kaggle.com/gpiosenka/100-bird-species

One potential source of performance benchmarks: https://www.kaggle.com/gpiosenka/100-bird-species

The HTML formatted report can be found here on GitHub.

Multi-Class Image Classification Deep Learning Model for Kaggle 275 Bird Species 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 Kaggle 275 Bird Species dataset is a multi-class classification situation where we attempt to predict one of several (for this dataset 275) possible outcomes.

INTRODUCTION: This dataset contains 275 bird species with 39364 training images, 1375 test images (5 per species), and 1375 validation images (5 per species. All images have a resolution of 224 X 224 X 3 color images in the jpg format. Each dataset includes 275 subdirectories, one for each bird species.

In this Take1 iteration, we will construct a simple three-layer CNN model to predict the species for the image.

ANALYSIS: The performance of the baseline model achieved an accuracy score of 68.87% after 50 epochs using the validation dataset. The same model processed the test dataset with an accuracy score of 69.24%.

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

Dataset Used: Kaggle 275 Bird Species dataset

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

Dataset Reference: https://www.kaggle.com/gpiosenka/100-bird-species

One potential source of performance benchmarks: https://www.kaggle.com/gpiosenka/100-bird-species

The HTML formatted report can be found here on GitHub.