rupertmenneer

bayesian_flow

A repo reproducing discrete/discretised Bayesian Flow Networks https://arxiv.org/abs/2308.07037 for MNIST and CIFAR10 datasets

checkers

A checkers game with a min-max AI opponent

cifar-10

CNNs applied to the CIFAR-10 task. Highest achieving model is based upon the ResNet Architecture and achieved an accuracy of 92.3%.

convcnp

Implementation of the Convolutional Conditional Neural Process

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

edm2_dual_gnn

Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)

facial-alignment

This notebook presents a method for achieving efficient millisecond facial alignment with a cascade of gradient boosted trees

GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

ucc_roberta

rupertmenneer/ucc_roberta

rupertmenneer/bayesian_flow

A repo reproducing discrete/discretised Bayesian Flow Networks https://arxiv.org/abs/2308.07037 for MNIST and CIFAR10 datasets

rupertmenneer/checkers

A checkers game with a min-max AI opponent

rupertmenneer/cifar-10

CNNs applied to the CIFAR-10 task. Highest achieving model is based upon the ResNet Architecture and achieved an accuracy of 92.3%.

rupertmenneer/convcnp

Implementation of the Convolutional Conditional Neural Process

rupertmenneer/diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

rupertmenneer/DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

rupertmenneer/facial-alignment

This notebook presents a method for achieving efficient millisecond facial alignment with a cascade of gradient boosted trees

rupertmenneer/GFPGAN

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

rupertmenneer/guided-diffusion

rupertmenneer/mphil-intro-module

Jupyter notebooks on inference, regression and classification for MPhil students

rupertmenneer/mrscc

Using the Hugging Face Trainer I use the RoBERTa model to compete in the Microsoft Research Sentence Completion Challenge to achieve an accuracy of 82.6. A CBOW model is also implemented on the MRSCC. Notebooks are provided for both models.

rupertmenneer/Neural-Process-Family

Code for the Neural Processes website and replication of 4 papers on NPs. Pytorch implementation.

rupertmenneer/neural-processes

Pytorch implementation of Neural Processes for functions and images :fireworks:

rupertmenneer/pykenlm

KenLM: Faster and Smaller Language Model Queries