Sources

• Guide to convolution: https://arxiv.org/pdf/1603.07285.pdf
• Beginner's guide to GANs: https://pathmind.com/wiki/generative-adversarial-network-gan
• Architecture of a GAN: https://subscription.packtpub.com/book/big_data_and_business_intelligence/9781789136678/1/ch01lvl1sec12/the-detailed-architecture-of-a-gan
• Guide to the Generator: https://developers.google.com/machine-learning/gan/generator
• Feature scaling: https://en.wikipedia.org/wiki/Feature_scaling
• DCGAN (TensorFlow): https://www.tensorflow.org/tutorials/generative/dcgan
• DCGAN (arXiv): https://arxiv.org/pdf/1511.06434.pdf
• DCGAN (Stanford) (the main DCGAN source I used): http://stanford.edu/class/ee367/Winter2017/yan_wang_ee367_win17_report.pdf
• FCGAN: https://arxiv.org/pdf/1905.02417.pdf
• Identity mapping (how I learned residuals): https://arxiv.org/pdf/1603.05027.pdf
• Deep Residual Learning (how I learned residuals part 2): https://arxiv.org/pdf/1512.03385.pdf
• Convolutional backpropagation: https://medium.com/@pavisj/convolutions-and-backpropagations-46026a8f5d2c
• Extra info on partial convolution: https://arxiv.org/pdf/1804.07723.pdf
• Partial convolution based padding: https://arxiv.org/pdf/1811.11718.pdf
• Info on checkerboard artifacts: https://distill.pub/2016/deconv-checkerboard/
• Wasserstein GAN: https://arxiv.org/pdf/1701.07875.pdf
• Wasserstein GAN tutorial: https://machinelearningmastery.com/how-to-code-a-wasserstein-generative-adversarial-network-wgan-from-scratch/
• Wasserstein loss tutorial: https://machinelearningmastery.com/how-to-implement-wasserstein-loss-for-generative-adversarial-networks/