Binary Class Image Classification Deep Learning Model for CycleGAN Cezanne vs. Photo 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 CycleGAN Cezanne vs. Photo dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The CycleGAN dataset collection contains images from two classes A and B (for example, apple vs. orange, horses vs. zebras, and so on). The researchers used the images to train machine learning models for research work in General Adversarial Networks (GAN).

In this iteration, we will construct a CNN model based on the VGG16 architecture to make predictions.

ANALYSIS: In this iteration, the VGG16 model’s performance achieved an accuracy score of 98.46% after ten epochs using the training dataset. The same model processed the validation dataset with an accuracy measurement of 97.36%. Finally, the final model processed the test dataset with an accuracy score of 99.01%.

CONCLUSION: In this iteration, the VGG16-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: CycleGAN Cezanne vs. Photo Dataset

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://people.eecs.berkeley.edu/%7Etaesung_park/CycleGAN/datasets/

One potential source of performance benchmarks: https://arxiv.org/abs/1703.10593 or https://junyanz.github.io/CycleGAN/

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for CycleGAN Cezanne vs. Photo 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 CycleGAN Cezanne vs. Photo dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The CycleGAN dataset collection contains images from two classes A and B (for example, apple vs. orange, horses vs. zebras, and so on). The researchers used the images to train machine learning models for research work in General Adversarial Networks (GAN).

In this iteration, we will construct a CNN model based on the DenseNet121 architecture to make predictions.

ANALYSIS: In this iteration, the DenseNet121 model’s performance achieved an accuracy score of 99.80% after ten epochs using the training dataset. The same model processed the validation dataset with an accuracy measurement of 98.90%. Finally, the final model processed the test dataset with an accuracy score of 99.87%.

CONCLUSION: In this iteration, the DenseNet121-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: CycleGAN Cezanne vs. Photo Dataset

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://people.eecs.berkeley.edu/%7Etaesung_park/CycleGAN/datasets/

One potential source of performance benchmarks: https://arxiv.org/abs/1703.10593 or https://junyanz.github.io/CycleGAN/

The HTML formatted report can be found here on GitHub.

Algorithmic Trading Model using Force Index with Different Periods

NOTE: This script is for learning purposes only and does not constitute a recommendation for buying or selling any stock mentioned in this script.

SUMMARY: This project aims to construct and test an algorithmic trading model and document the end-to-end steps using a template.

INTRODUCTION: This algorithmic trading model employs a simple mean-reversion strategy for stock position entries and exits using force index indicators. For the Force Index indicator, the model will use a 13-period and a 50-period indicator for the trading signal. The model will initiate a long position when the trading indicator turns from negative to positive. Conversely, the model will exit the long position when the signal indicator turns from positive to negative.

ANALYSIS: In this modeling iteration, we analyzed ten stocks between August 1, 2016, and September 17, 2021. The models’ performance appeared at the end of the script. The models with the wider signal line width generally produced a better return for the tested stocks. Moreover, the simple buy-and-hold approach came out ahead for all stocks.

CONCLUSION: For most stocks during the modeling time frame, the long-only trading strategy with the Force Index did not produce a better return than the buy-and-hold approach. We should consider modeling these stocks further by experimenting with more variations of the strategy.

Dataset ML Model: Time series analysis with numerical attributes

Dataset Used: Quandl

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for CycleGAN Cezanne vs. Photo 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 CycleGAN Cezanne vs. Photo dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The CycleGAN dataset collection contains images from two classes A and B (for example, apple vs. orange, horses vs. zebras, and so on). The researchers used the images to train machine learning models for research work in General Adversarial Networks (GAN).

In this iteration, we will construct a CNN model based on the ResNet50V2 architecture to make predictions.

ANALYSIS: In this iteration, the ResNet50V2 model’s performance achieved an accuracy score of 99.49% after ten epochs using the training dataset. The same model processed the validation dataset with an accuracy measurement of 98.53%. Finally, the final model processed the test dataset with an accuracy score of 98.51%.

CONCLUSION: In this iteration, the ResNet50V2-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: CycleGAN Cezanne vs. Photo Dataset

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://people.eecs.berkeley.edu/%7Etaesung_park/CycleGAN/datasets/

One potential source of performance benchmarks: https://arxiv.org/abs/1703.10593 or https://junyanz.github.io/CycleGAN/

The HTML formatted report can be found here on GitHub.

Binary Class Image Classification Deep Learning Model for CycleGAN Cezanne vs. Photo 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 CycleGAN Cezanne vs. Photo dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The CycleGAN dataset collection contains images from two classes A and B (for example, apple vs. orange, horses vs. zebras, and so on). The researchers used the images to train machine learning models for research work in General Adversarial Networks (GAN).

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 99.65% after ten epochs using the training dataset. The same model processed the validation dataset with an accuracy measurement of 98.24%. Finally, the final model processed the test dataset with an accuracy score of 99.75%.

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: CycleGAN Cezanne vs. Photo Dataset

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://people.eecs.berkeley.edu/%7Etaesung_park/CycleGAN/datasets/

One potential source of performance benchmarks: https://arxiv.org/abs/1703.10593 or https://junyanz.github.io/CycleGAN/

The HTML formatted report can be found here on GitHub.

Jeff Goins on Real Artists Don’t Starve, Part 6

In his book, Real Artists Don’t Starve: Timeless Strategies for Thriving in the New Creative Age, Jeff Goins discusses how we can apply prudent strategies in positioning ourselves for thriving in our chosen field of craft.

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

Chapter 6, Go Join a Scene

In this chapter, Jeff discusses the importance of where we do our work and its effect on our work. He offers the following recommendations for us to think about:

  • Our environment can affect how others perceive our work. One way it does that is by affecting the network we can build in that environment. Different settings allow us to create various networks. Those networks can contribute both positively and negatively to our work.
  • As an artist, we must be good at what we do, but being good is not enough. We must also have access to influential people who can help us spread our work and ideas. A network is our insurance against anonymity.
  • An artist will inevitably ensure many rejections. There will be many people who would reject our work for a variety of reasons. When we get rejected repeatedly, sometimes the best approach is not to work harder but to change the location or the scenery.
  • Not everyone can move to another location on a whim. Sometimes we need to stay where we are. Therefore, it is essential to create a scene or environment conducive to doing our work. There are tools for creating meet-ups and opportunities for like-minded individuals to connect locally. Sometimes the community we need could be right in front of us.
  • Success in any creative field is contingent on the scenes and the networks we are part of. First, we can build a network by contributing more than we take from it. Then, as we make those contributions over time, we will create a group of relationships, or networks, that we can take with us wherever we go.

In summary, “The Starving Artist believes he can be creative anywhere. The Thriving Artist goes where creative work is already happening.”

Binary Class Image Classification Deep Learning Model for CycleGAN Monet vs. Photo 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 CycleGAN Monet vs. Photo dataset is a binary classification situation where we attempt to predict one of two possible outcomes.

INTRODUCTION: The CycleGAN dataset collection contains images from two classes A and B (for example, apple vs. orange, horses vs. zebras, and so on). The researchers used the images to train machine learning models for research work in General Adversarial Networks (GAN).

In this iteration, we will construct a CNN model based on the VGG16 architecture to make predictions.

ANALYSIS: In this iteration, the VGG16 model’s performance achieved an accuracy score of 96.81% after ten epochs using the training dataset. The same model processed the validation dataset with an accuracy measurement of 94.49%. Finally, the final model processed the test dataset with an accuracy score of 96.56%.

CONCLUSION: In this iteration, the VGG16-based CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.

Dataset Used: CycleGAN Monet vs. Photo Dataset

Dataset ML Model: Binary classification with numerical attributes

Dataset Reference: https://people.eecs.berkeley.edu/%7Etaesung_park/CycleGAN/datasets/

One potential source of performance benchmarks: https://arxiv.org/abs/1703.10593 or https://junyanz.github.io/CycleGAN/

The HTML formatted report can be found here on GitHub.