Eric Elmoznino's repositories
deep_bilateral_network
PyTorch implementation of https://github.com/google/hdrnet for black-box image transformation
distribution_clustering
Implements (high-dimenstional) clustering algorithm described in https://arxiv.org/pdf/1804.02624.pdf
MusicGenerator
A deep belief net coupled with a recurrent LSTM network that composes original piano pieces. Implemented in TensorFlow.
neural_scene_representation
Train a GQN neural network and compare its representational structure to that of scene regions from human fMRI data.
syntax_tree_network
Tree-structured neural network that uses explicit syntax as an inductive bias to learn compositional representations of language.
StochasticNeuralNetwork
Experimentations training a stochastic neural network on MNIST data
adversarial_tms
Code to adversarially manipulate an image using gradients through an encoding model such that activity in only a targeted brain region is affected, simulating the effect of TMS.
CellSegmentation
Segments the nucleus in images with multiple cells of a different type
coremltools
Converter tools for Core ML.
ece421-a1
Assignment 1 for the ECE421 class at UofT
ece421-a2
Assignment 2 for the ECE421 class at UofT
ece421-a3
Assignment 3 for the ECE421 class at UofT
pyro_gmmvae
A VAE implemented in Pyro with a Gaussian Mixture Model specifying the prior or latent variables. The Gaussian Mixture prior encourages natural clustering of the latent space according to the classes of the data. It also permits the generation of a desired class after training, since we can manually select which Gaussian component to sample from in order to generate a sample from p(x|z).
pytorch-hed
a reimplementation of Holistically-Nested Edge Detection in PyTorch
PyTorch_Tutorial
An explanation of what PyTorch is, the advantages it provides relative to other frameworks, and a complete example with model saving/loading, fine-tuning, and data augmentation
rsa_emd
Earth Mover's Distance for computing brain pattern similarity in RSA
scene_generator
Generate a dataset of simple random scene specifications
semantic-segmentation-pytorch
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
unity_fmri_scene_representation
Unity environment for running fMRI experiments in the GQN scene representation project