The goal for the project is to be able to transform a given picture with a given pattern for creating art pictures. The source of the modification will be the CNN. This network will be trained to extract specific features and patterns from a set of specific images. After, by applying a picture in the net, the picture will be modified to a new image that are mixed with the features and patterns extracted from the set.
This repository contains all the ressources:
- Our reports and realizations
- Reshearch papers
- Documents from other people
- Website links
All the other repositories that we used for our expimentations can be cloned inside the main folder of this repository. The folder will be ignore by git. The list of all the other projects is in the next section.
DeepDream is a computer vision program created by Google which uses a convolutional neural network to find and enhance patterns in images via algorithmic pareidolia, thus creating a dreamlike hallucinogenic appearance in the deliberately over-processed images. [Wikipedia definition]
This project is used for understanding how to use a convolutional neural network for adding patterns to an image.
[email protected]:DD2427-Deep-Learning-Project/deepdream.git