Justus Perillieux

PyTorch implementation of "Super-Realtime Facial Landmark Detection and Shape Fitting by Deep Regression of Shape Model Parameters" predicting facial landmarks with up to 400 FPS

PyTorch Implementation of the Deep Alignment Network

Utilities for Deep Learning with PyTorch (models, losses, metrics etc.)

This repository contains my implementation of a shape-constrained network which predicts up to 170 FPS

No description.

library to modify images and the corresponding landmarks

Under Construction

A baseline repository to train a unet with delira

No description.

Some miscellaneous PyTorch stuff

No description.

Dockerfiles to development lightning on cuda and docker

version-string management for VCS-controlled trees

Custom PyTorch layers to add useful features

Train Scripts for the vision package

Helpful utilities for deep learning in medical image analysis/medical image computing

No description.

A delira-compatible cycle-GAN skeleton.

Solving the Traveling Salesman Problem using Self-Organizing Maps

A Probabilistic U-Net for segmentation of ambiguous images implemented in PyTorch

Things3.app MCP Server

CLI tool to move Neptune experiments (version 2.x or 3.x) to disk as parquet + files, with an option to load them into MLflow or Weights & Biases.

Remote development in Neovim 🔥

TorchIO: medical imaging for deep learning.

Magic to turn Cursor/Windsurf as 90% of Devin

Homebrew installation manager for nix-darwin

No description.

No description.

A modern Neovim configuration with full battery for Python, Lua, C++, Markdown, LaTeX, and more...

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Ongoing research training transformer models at scale

No description.

An oh-my-zsh theme.

No description.

A configuration for Neovim beginners.

Draft of the fastai book

No description.

The full minitorch student suite.

My Neovim configuration with Lua

A LaTeX / XeLaTeX / LuaLaTeX PhD thesis template for Cambridge University Engineering Department (CUED)

An end-to-end implementation of intent prediction with Metaflow and other cool tools

Personal Ansible Configuration for Desktop and Server

Run Orthanc DICOM Server on Synology DiskStation

Ansible role for installing and managing the Slurm Workload Manager

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

No description.

Theia applications - docker images and desktop distributions

The website for PyTorch

No description.

A framework for data augmentation for 2D and 3D image classification and segmentation

No description.

A PyTorch Implementation of FaceBoxes

denas - A delira compatible PyTorch port of "Efficient Neural Architecture Search via Parameters Sharing"

A flexible framework of neural networks for deep learning

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

GANnotation (PyTorch): Landmark-guided face to face synthesis using GANs (And a triple consistency loss!)

Client code for Jasper voice computing platform

A PyTorch implementation of "Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights"

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

A statistical modelling toolkit, providing all the tools required to build, fit, visualize, and test deformable models.

Menpo's 2D deformable modelling toolkit (AAMs/CLMs/SDMs)

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

A deep neural network for face alignment

Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).

Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)

Simple tutorials using Google's TensorFlow Framework

Manage your machine learning experiments with trixi - modular, reproducible, high fashion. An experiment infrastructure optimized for PyTorch, but flexible enough to work for your framework and your tastes.

No description.

This repository contains an early stage of suggestive segmentation using a u-net. It has been abandoned in favor of more accurate segmentation approaches.

A PyTorch Implementation of SphereFace.

Spectral Analysis Task

No description.

No description.