Commit c2c1d574 authored by Rita-Josy Haddoub's avatar Rita-Josy Haddoub
Browse files

Update README.md

parent fc90d9e2
......@@ -9,7 +9,7 @@ This is the pretrained model for _Béton_, along with its raw image dataset. Th
A collection of photographs showing found Béton have been stored in a dedicated image dataset. With this dataset, I am exploring ways that _‘Machine Learners’_ refers to humans as much as it does to computers. As a single _‘variable’_ which represents experimentation and fragmentation, _Béton_ can be computationally seen within the ‘Latent Space.’ The Latent space is the hidden layer of machine learning which breaks its’ input apart, and tries to re-assemble it by learning possible compositions. To visualize the latent space, I feed my image dataset of _Béton_ to a network that de-codes this inner process and generates the re-done _Béton_.
**[Click here](http://igor.gold.ac.uk/~rhadd001/GANtoBeton/) to see a simulated display for an exhibition.**
Projection of a photo-grid on an entire wall surface.The photo-grid shuffles through the entire jpg images fed through and produced by the Beton GAN model. So it includes my cropped 256x256 image dataset, the computed test-set, and the reconstructed visualization(latent image).
Projection of a photo-grid on an entire wall surface.The photo-grid shuffles through the entire training data, and the predictions of the trained model.
The Beton sculptures would be displayed physically either on the floor or on plinths.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment