Saturday, April 17, 2021
  • Setup menu at Appearance » Menus and assign menu to Top Bar Navigation
Advertisement
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
No Result
View All Result
Home Neural Networks

Generating New Pokemons Using GANs

November 15, 2019
in Neural Networks
Generating New Pokemons Using GANs
586
SHARES
3.3k
VIEWS
Share on FacebookShare on Twitter

For this project, I will be using the PyTorch framework and a Pokémon Image Dataset on Kaggle. In this project, I will be creating a Deep Convolutional GAN to generate fake Pokémon images. A DCGAN is a type of GAN that excels at producing image content as it contains Convolutional Layers.

Training Parameters

To begin, we will need to define some inputs and parameters for setting the neural network architectures as well as training.

You might also like

AI and Human Rights, A Story About Equality | by bundleIQ | Mar, 2021

The “Blue Brain” Project-A mission to build a simulated Brain | by The A.I. Thing | Mar, 2021

Templates Vs Machine Learning OCR | by Infrrd | Mar, 2021

Input Data

Here is a sample of the Pokémon images that make up the dataset. For my model, I decided to downscale the images to 64 x 64 for an efficient process and data normalization. A DCGAN prefers a three-channel input (RGB); however, since the dataset had a transparent background, it had four channels (RGBA — A is referring to the alpha channel). It is recommended that you convert these to RGB images for improved performance; however, I lazily decided to skip this step 😁.

Generator

Now that we have our data, we can start off defining the architecture for the generator model. Given the latent vector as input, the generator outputs an image matching the images in the dataset 3 x 64 x 64. The model itself has five convolutional layers for making the image and its layers. Each convolutional layer is followed by batch normalization to improve the efficiency and stability of the network. Also, the model uses ReLU as its activation function (except for the final being a tan hyperbolic function). It is important to note that the network is initialized with a random set of weights and biases, resulting in noise.

Discriminator

The discriminator architecture is very similar to the generator as it has the same overall structure. The main difference is that the LeakyReLU and Sigmoid activation functions are used. Instead of suing convolutional layers that produce content, convolutional layers are used for classification. Similar to the generator, the discriminator is also initialized with a random set of weights and biases.

Loss Functions and Optimizers

The loss function used is the BCELoss function in PyTorch, which is a Binary Cross-Entropy Loss function. This loss function is optimal loss function for targets (output) between 0 (fake) and 1 (real), making it practical for our model.

For both networks, we will be using Adam Optimizers from PyTorch and is an adaptive learning rate optimization algorithm.

Training Time!

The time has come to put our GAN to work and initialize the training process. To do, we must define the generator and discriminator loss (this involves some math which I will skip for simplicity’s sake). Once we set up the training loop, we can just let the loop run for the number of epochs we defined earlier. I trained my model for 2500 epochs/iterations.

The Results Are In!

Well, the results were interesting, to say the least. I particular found it interesting how many of the fake Pokémon’s looked the same. But, I will let you be the judge of the quality of the fakes. I think it is pretty interesting, and I can see a couple of the fakes serving as inspiration for legitimate future Pokémon’s. The most interesting is the variation of Pokémons between various epochs or iterations of the GAN.

Results of the training process over 2500 iterations (every frame is recorded every 100 iterations).

You can check out the Google Colab Interactive Notebook to train the GAN yourself and make some tweaks!

Credit: BecomingHuman By: Jatin Mehta

Previous Post

When one isn’t enough: This shady malware will infect your PC with dual Trojans

Next Post

AI, machine learning can help throughput in doctor visits, lab tests and procedures: Kris Gopalakrishnan

Related Posts

AI and Human Rights, A Story About Equality | by bundleIQ | Mar, 2021
Neural Networks

AI and Human Rights, A Story About Equality | by bundleIQ | Mar, 2021

April 17, 2021
The “Blue Brain” Project-A mission to build a simulated Brain | by The A.I. Thing | Mar, 2021
Neural Networks

The “Blue Brain” Project-A mission to build a simulated Brain | by The A.I. Thing | Mar, 2021

April 17, 2021
Templates Vs Machine Learning OCR | by Infrrd | Mar, 2021
Neural Networks

Templates Vs Machine Learning OCR | by Infrrd | Mar, 2021

April 16, 2021
Artificial Intelligence in Radiology — Advantages, Use Cases & Trends | by ITRex Group | Apr, 2021
Neural Networks

Artificial Intelligence in Radiology — Advantages, Use Cases & Trends | by ITRex Group | Apr, 2021

April 16, 2021
A simple explanation of Machine Learning and Neural Networks and A New Perspective for ML Experts | by Akhilesh Ravi | Apr, 2021
Neural Networks

A simple explanation of Machine Learning and Neural Networks and A New Perspective for ML Experts | by Akhilesh Ravi | Apr, 2021

April 15, 2021
Next Post
AI, machine learning can help throughput in doctor visits, lab tests and procedures: Kris Gopalakrishnan

AI, machine learning can help throughput in doctor visits, lab tests and procedures: Kris Gopalakrishnan

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Recommended

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

January 6, 2019
Microsoft, Google Use Artificial Intelligence to Fight Hackers

Microsoft, Google Use Artificial Intelligence to Fight Hackers

January 6, 2019

Categories

  • Artificial Intelligence
  • Big Data
  • Blockchain
  • Crypto News
  • Data Science
  • Digital Marketing
  • Internet Privacy
  • Internet Security
  • Learn to Code
  • Machine Learning
  • Marketing Technology
  • Neural Networks
  • Technology Companies

Don't miss it

10 Popular Must-Read Free eBooks on Machine Learning
Machine Learning

10 Popular Must-Read Free eBooks on Machine Learning

April 17, 2021
Security crucial as 5G connects more industries, devices
Internet Security

Security crucial as 5G connects more industries, devices

April 17, 2021
Relay Therapeutics pays $85M for startup with a new AI tech for drug discovery
Machine Learning

Relay Therapeutics pays $85M for startup with a new AI tech for drug discovery

April 17, 2021
Google releases Chrome 90 with HTTPS by default and security fixes
Internet Security

Google releases Chrome 90 with HTTPS by default and security fixes

April 17, 2021
ML Scaling Requires Upgraded Data Management Plan
Machine Learning

ML Scaling Requires Upgraded Data Management Plan

April 17, 2021
SolarWinds cybersecurity spending tops $3 million in Q4, sees $20 million to $25 million in 2021
Internet Security

SolarWinds: US and UK blame Russian intelligence service hackers for major cyberattack

April 17, 2021
NikolaNews

NikolaNews.com is an online News Portal which aims to share news about blockchain, AI, Big Data, and Data Privacy and more!

What’s New Here?

  • 10 Popular Must-Read Free eBooks on Machine Learning April 17, 2021
  • Security crucial as 5G connects more industries, devices April 17, 2021
  • Relay Therapeutics pays $85M for startup with a new AI tech for drug discovery April 17, 2021
  • Google releases Chrome 90 with HTTPS by default and security fixes April 17, 2021

Subscribe to get more!

© 2019 NikolaNews.com - Global Tech Updates

No Result
View All Result
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News

© 2019 NikolaNews.com - Global Tech Updates