Implementing a GAN from scratch using PyTorch

[DeewakarChakraborty]

Implementing a GAN from scratch using PyTorch

Introduction paragraph (2-3 paragraphs):

Machine learning algorithms work great in recognizing patterns in existing data and using that insight for classification and regression purposes. However, the machine always struggled when asked to generate new data. This all changed in 2014 when Ian Goodfellow introduced Generative Adversarial Networks (GANs) to the world of machine learning. This technique enabled machines to generate realistic data. GANs are the class of ML techniques that consist of two simultaneously trained neural networks, one is Generator which is used to generate the fake data, and the other is Discriminator which is used to classify whether input given to it is real (data from training dataset) or fake (data generated by the discriminator). In this blog, we will understand the science behind GANs and implement one from scratch using PyTorch.

Key takeaways:

• Introduction to generative modeling
• What are GANs?
• What are the different types of GAN?
• How GANs work
• Implementing a GAN from scratch using PyTorch.

References:

NA

Templates to use as guides

• How To Guide Template
• Software Review Template
• Tutorial Template

[ahmadmardeni1]

Good afternoon and thank you for submitting your topic suggestion. @DeewakarChakraborty Your topic form has been entered into our queue and should be reviewed (for approval) as soon as a content moderator is finished reviewing the ones in the queue before it.

[lalith1403]

Great topic 🚀 , make sure it matches the following:

• Adds value beyond what is in the official docs and what is covered in other blog sites.
• To avoid potential article closure, it should not overlap with existing EngEd articles or incoming topic suggestions.

Please reference any relevant EngEd articles in yours and build a unique project - Approved. @DeewakarChakraborty