Christopher Beckham's repositories
hologan-pytorch
Non-official + minimal reimplementation of HoloGAN by Nguyen-Phuoc, et al: https://arxiv.org/abs/1904.01326
coms-are-energy-models
Official code for paper: Conservative objective models are a special kind of contrastive divergence-based energy model
challenges-few-shot-gans
Official repository for "Overcoming challenges in leveraging GANs for few-shot data augmentation", accepted to CoLLAs 2022.
design-bench-setup
Containing repository of my Design Bench fork, as well as Mujoco install instructions at Mila
simple-ebms
Contrastive-divergence EBMs on toy 2D datasets. Can be trained and visualised with a simple API.
autoscript
Convert a .json file specifying hyperparameters to individual shell scripts to be executed
design-bench
Benchmarks for Model-Based Optimization
amdim-public
Public repo for Augmented Multiscale Deep InfoMax representation learning
choosem
dropdown picker/launcher for mac os
clevr-dataset-gen
A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
continual_learning_papers
Relevant papers in Continual Learning
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
ncsnv2
The official PyTorch implementation for NCSNv2 (NeurIPS 2020)
neuraloperator
Learning in infinite dimension with neural operators.
NVAE
The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
precision-recall-distributions
Assessing Generative Models via Precision and Recall (official repository)
sharadvikram.com
My personal vanity page
SimCLR
A PyTorch implementation of SimCLR based on ICML 2020 paper "A Simple Framework for Contrastive Learning of Visual Representations"
thesis-ipython-notebooks
IPython notebooks accompanying my thesis.
validate-args
Quick and easy code to validate experiment args / insert default args for my Haven-based workflow.
vdvae
Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"