solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

This repository contains implementations and illustrative code to accompany DeepMind publications

OpenRefine is a free, open source power tool for working with messy data and improving it

Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks. Support: https://discourse.slicer.org/c/community/radiomics

[ICCV2021] Official PyTorch implementation of Segmenter: Transformer for Semantic Segmentation

Best Practices on Recommendation Systems

Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

Visualizations for machine learning datasets

Deep Learning-based Frozen Section to FFPE Translation

Fast and Scalable Image Search for Histology

Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks - MICCAI 2021

An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come

Recursive Ensemble Feature Selection

Image augmentation for machine learning experiments.

VOLO: Vision Outlooker for Visual Recognition

The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

DSMIL: Multiple instance learning networks for tumor detection in Whole Slide Image

Generation of synthetic artefacts / digital pathology

Interactive Segmentation of Nucleus

Clairvoyance: a Unified, End-to-End AutoML Pipeline for Medical Time Series

This repository contains demos I made with the Transformers library by HuggingFace.

Multiplex Immunoflouresence Titration Optimization (mIFTO) R Package

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

ISTR: End-to-End Instance Segmentation with Transformers (https://arxiv.org/abs/2105.00637)

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO