Notebook 1 : Goal In this notebook, you're going to create your first generative adversarial network (GAN) for this course! Specifically, you will build and train a GAN that can generate hand-written images of digits (0-9). You will be using PyTorch in this specialization, so if you're not familiar with this framework, you may find the PyTorch documentation useful https://pytorch.org/docs/stable/index.html . The hints will also often include links to relevant documentation. Learning Objectives Build the generator and discriminator components of a GAN from scratch. Create generator and discriminator loss functions. Train your GAN and visualize the generated images.
Hyperspherical Variational Auto-Encoders (Davidson, Falorsi, De Cao, Kipf, and Tomczak, 2018): https://www.researchgate.net/figure/Latent-space-visualization-of-the-10-MNIST-digits-in-2-dimensions-of-both-N-VAE-left_fig2_324182043
Analyzing and Improving the Image Quality of StyleGAN (Karras et al., 2020): https://arxiv.org/abs/1912.04958
Semantic Image Synthesis with Spatially-Adaptive Normalization (Park, Liu, Wang, and Zhu, 2019): https://arxiv.org/abs/1903.07291
Few-shot Adversarial Learning of Realistic Neural Talking Head Models (Zakharov, Shysheya, Burkov, and Lempitsky, 2019): https://arxiv.org/abs/1905.08233
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (Wu, Zhang, Xue, Freeman, and Tenenbaum, 2017): https://arxiv.org/abs/1610.07584
These Cats Do Not Exist (Glover and Mott, 2019): http://thesecatsdonotexist.com/
From the notebooks:
Large Scale GAN Training for High Fidelity Natural Image Synthesis (Brock, Donahue, and Simonyan, 2019): https://arxiv.org/abs/1809.11096
PyTorch Documentation: https://pytorch.org/docs/stable/index.html#pytorch-documentation
MNIST Database: http://yann.lecun.com/exdb/mnist/