Christopher Beckham, PhD's repositories
gan-heightmaps
Procedural terrain generation for video games has been traditionally been done with smartly designed but handcrafted algorithms that generate heightmaps. We propose a first step toward the learning and synthesis of these using recent advances in deep generative modelling with openly available satellite imagery from NASA.
cnn-energy-model
A Theano implementation of a CNN DSEBM (deep structured energy-based model) described in https://arxiv.org/pdf/1605.07717v2.pdf
cyclegan-lasagne
A Lasagne implementation of CycleGAN.
pix2pix-lasagne
An implementation of pix2pix (conditional GANs for image-to-image translation) in Lasagne: https://arxiv.org/abs/1611.07004
acgan-lasagne
acgan
ALI-lasagne
Adversarially learned inference in Lasagne
comp767
All my presentations/reports + final project for the COMP767 reinforcement learning class at McGill.
crfrnn_layer
A Lasagne layer (and supporting Theano Ops) for the CRF-as-RNN layer.
ecuador-moths
Images of Ecuador Moths for Fine-grained Recognition
genegan-lasagne
An implementation of GeneGAN in Lasagne
lasagne-vae
Variational-autoencoder notebooks and code in Lasagne
lasagne_stuff
Random stuff that could be useful for Lasagne
learning-tensorflow
Learning TensorFlow with Eugene
pix2pix-tensorflow
Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/
pytorch-grad-cam
PyTorch implementation of Grad-CAM
quadratic-weighted-kappa
Implementation of quadratic weighted kappa in Lasagne
reinforcement-learning
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
TensorFlow-Examples
TensorFlow Tutorial and Examples for beginners
tsne-d3-python
Visualize high dimensional data with t-sne using D3 and Python
vess2ret
A Keras implementation of pix2pix code adapted to generate retinal images from vessel networks.
weightnorm
Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks"
wgan-gp
A pytorch implementation of Paper "Improved Training of Wasserstein GANs"