Mnpr / Art-Generation-GANs

:art: Series of progressive exploration and experimentation of Deep Generative Models on subset of WikiArt dataset to produce Realistic art Images.

This repository contains Master Projectwork ⬇️ undertaken for the partial fulfillment of M.S. in Information Engineering @Fachhochschule-Kiel under the supervision of Prof. Dr. Hauke Schramm

Exploration of Art Generation using Deep Generative models (GANs).

Objective : Series of progressive exploration and experimentation of Deep Generative Models on subset of Wiki-Art dataset to produce Realistic art Images.

🎨 Datasets

Source : Wiki-Art : Visual Art Encyclopedia

Dataset Contents for Unconditional Generation

'abstract': 14999,
'animal-painting': 1798,
'cityscape': 6598,
'figurative': 4500,
'flower-painting': 1800,
'genre-painting': 14997,
'landscape': 15000,
'marina': 1800,
'mythological-painting': 2099,
'nude-painting-nu': 3000,
'portrait': 14999,
'religious-painting': 8400,
'still-life': 2996,
'symbolic-painting': 2999

Resized subsets for Conditional Generation

• abstract,cityscape, landscape,portrait ( no. of samples > 5000 )

photo2fourcollection for multi-collection style transfer

• train_content, test_content, train_styles

ℹ️ Instructions / Information

• System Setup

• Dataset Instructions (Extract[ Download ], Transform, & Load)

• Training and Logging

💻 Explored / Implemented Architectures

• Unconditional Generation

  • FullyConnected MLP-GAN

  • DeepConvolutional-GAN

  • Wasserstein-GAN

    • Weight Clipping
    • Gradient Penalty

• Conditional Generation

  • Conditional-DCGAN

• Style Based Generation

  • Neural Style Transfer
  • Multi Collection Style Transfer( GatedGAN )

📑 References

• [ 1 ] Generative Adversarial Nets [ arXiv:1406.2661v1 [stat.ML] 10 Jun 2014 ]

• [ 2 ] Conditional Generative Adversarial Nets [arXiv:1411.1784v1 [cs.LG] 6 Nov 2014]

• [ 3 ] Unsupervised Representation Learning with Deep Convolutional GANs [ arXiv:1511.06434v2 [cs.LG] 7 Jan 2016 ]

• [ 4 ] Improved Techniques for Training GANs [ arXiv:1606.03498v1 [cs.LG] 10 Jun 2016 ]

• [ 5 ] Wasserstein GAN [ arXiv:1701.07875v3 [stat.ML] 6 Dec 2017 ]

• [ 6 ] Improved Training with WGAN-GP [ arXiv:1704.00028v3 [cs.LG] 25 Dec 2017 ]

• [ 7 ] Gated GAN: Adversarial Gated Networks for Multi-Collection Style Transfer [ arXiv:1904.02296v1 [cs.CV] 4 Apr 2019 ]

• [ 8 ] VGG-19 as Feature(style/semantics) Extractor - PyTorch Documentation

• [ 9 ] Coursera (Deeplearning.ai) - Build Basic GANs [ Online Course ]

• [ 10 ] GitHub - colemiller94/gatedgan: PyTorch Implementation of Lua [https://github.com/xinyuanc91/Gated-GAN]

• [ 11 ] GitHub - HarisIqbal88/PlotNeuralNet: Latex code for making neural networks diagrams

---