Neural Network Art

Frameworks  /  Neural Network Art

These images are examples of neural style transfer.

They are created using Gatys et al. 2015 algorithm ("A Neural Algorithm of Artistic Style") that minimizes a cost function that combines image content and image style. The images are generated using Tensorflow convolutional neural network libraries and a 19 layer VGG CNN trained by the MatConvNet team. Special thanks to for code frameworks and inspiration.

Content 1: Rey d'Aragon Steps in Bonefacio
Style 1: Cliff near Fecamp by Monet
Generated 1: Steps in Bonefacio by Monet
Content 2: Trumpet playing robot
Style 2: The Scream by Munch
Generated 2: Screaming robot trumpet
Content 3: Darren Wilkinson at the Tokyo Sky Tree
Style 3: Pablo Picasso self portrait (1917)
Generated 3: Picasso styled Wilkinson
Content 4: Crowd at Roland Garros
Style 4: Le Moulin de la Galette Pierre Auguste by Renior
Generated 4: Roland Renior
Content 5: Broadway Tower, Cotswolds, England
Style 5: Starry Night by Van Gogh
Generated 5: Starry Broadway Tower
+44 207 558 8728
3rd Floor, 207 Regent Street
London, W1B 3HH. UK
Interested in working in analytics and applied AI? Contact us at
Details on our data security and management policies here.
This site uses Google Analytics. Google collects cookies for tracking.