In this video we build a generative adversarial network based on convolutional neural networks and train it on the CelebA dataset. This is a huge improvement from the previous simple fully connected GAN implemented in previous videos.

DCGAN paper:
https://arxiv.org/abs/1511.06434

CelebA dataset used in video:
https://www.kaggle.com/dataset/504743cb487a5aed565ce14238c6343b7d650ffd28c071f03f2fd9b25819e6c9

Github Repository:
https://github.com/aladdinpersson/Machine-Learning-Collection

OUTLINE:

• 0:00 - Introduction
• 0:26 - Quick Paper Recap
• 4:31 - Implementation of Discriminator
• 9:38 - Implementation of Generator
• 15:27 - Weight initialization and test model
• 19:09 - Setup of training
• 31:36 - Training on MNIST
• 32:20 - Modifications to CelebA dataset
• 33:52 - Training on CelebA and ending

#pytorch #deep-learning #python #machine-learning #developer