Stars
Jumpstart CICD deployments in Microsoft Fabric
Format and convert Python docstrings and generates patches
A massively parallel, high-level programming language
The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes
Repository for the deep-learning framework DIVA-DAF which is build with historical document image analysis in mind.
A configuration as code language with rich validation and tooling.
Towards Writer Retrieval for Historical Datasets@ICDAR2023 - an unsupervised approach using NetRVLAD and Similarity Graph Reranking
Our solution for the OCR competition of the summer school of document analysis 2023
Build U-Nets for segmentation from pre-trained TorchVision models.
An uroboros program with 100+ programming languages
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
Official PyTorch implementation of SegFormer
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
Extendable version manager with support for Ruby, Node.js, Elixir, Erlang & more
Official implementation of Score-CAM in PyTorch
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Use streaming to train whole-slides images with single image-level labels, by reducing GPU memory requirements with 99%.
Keras implementation of the paper "3D MRI brain tumor segmentation using autoencoder regularization" by Myronenko A. (https://arxiv.org/abs/1810.11654).
Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)