This course covers the training and implementation of autoencoders (AE), denoising autoencoders (DAE), and variational autoencoders (VAE) using PyTorch. It also delves into generative adversarial networks (GANs) and their comparison with AE and VAE. Students will learn to train these models, analyze their kernels, and understand their applications as generative models and energy-based models. The course includes hands-on coding exercises and explores the architecture and training process of GANs. The intended audience for this course includes individuals interested in deep learning, generative models, and PyTorch.
AE, DAE, and VAE with PyTorch - Generative Adversarial Networks and Code
Overview
Syllabus
– 1st of April 2021
– Training an autoencoder AE PyTorch and Notebook
– Looking at an AE kernels
– Denoising autoencoder recap
– Training a denoising autoencoder DAE PyTorch and Notebook
– Looking at a DAE kernels
– Comparison with state of the art inpainting techniques
– AE as an EBM
– Training a variational autoencoder VAE PyTorch and Notebook
– A VAE as a generative model
– Interpolation in input and latent space
– A VAE as an EBM
– VAE embeddings distribution during training
– Generative adversarial networks GANs vs. DAE
– Generative adversarial networks GANs vs. VAE
– Training a GAN, the cost network
– Training a GAN, the generating network
– A possible cost network's architecture
– The Italian vs. Swiss analogy for GANs
– Training a GAN PyTorch code reading
– That was it :D
Taught by
Alfredo Canziani
