Generating Art using a DCGAN and the WikiArt dataset.
Generative Adversarial Networks (GANs) are a framework for teaching a DL model to capture the training data’s distribution in order to generate new data from that same distribution. They are made of two distinct models, a generator and a discriminator. My goal in this project was to form a direct extension of a GAN that explicitly uses convolutional and convolutional-transpose layers in the discriminator and generator, respectively. By training this model on the WikiArt dataset, I was able to produce resulting generated images that genuinely embody elements of real artwork.
See writeup.pdf in Results directory for more info.
Open and run cells in WikiArtGAN.ipynb or go to the live Google Colab notebook I'm experimenting with.