CreativeAI: Deep Learning for Graphics Tutorial Code
This is the example code accompanying the CreativeAI: Deep Learning for Graphics Course at Siggraph Asia 2018.
These Notebooks can be executed in Google Colaboratory with the following links. Make sure to select a runtime with GPU support (Runtime > Change runtime type) to get the best performance.
Linear Regression and Polynomial Regression
https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/linear_regression.ipynb https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/poly_regression.ipynb https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/poly_regression_polyfit.ipynb
Stochastic Gradient Descent vs. Gradient Descent
https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/sgd.ipynb
Multi-Layer Perceptron
Edge Filter 'Network'
https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/edge_filter.ipynb
Convolutional Network
Filter Visualizations
Weight Initialization Strategies
Colorization Network
https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/colorization.ipynb
Autoencoder
https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/autoencoder.ipynb
Variational Autoencoder
Generative Adversarial Network (GAN)
https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/gan.ipynb
Mirroring with a Convolutional Network
https://colab.research.google.com/github/smartgeometry-ucl/dl4g/blob/master/mirroring.ipynb
PDE Learning (not available as notebook)
https://github.com/smartgeometry-ucl/dl4g/tree/master/pde_learning