Lars Vögtlin's starred repositories
summer-school-2023-competition
Our solution for the OCR competition of the summer school of document analysis 2023
backboned-unet
Build U-Nets for segmentation from pre-trained TorchVision models.
quine-relay
An uroboros program with 100+ programming languages
segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
finetuning-scheduler
A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.
copilot-docs
Documentation for GitHub Copilot
pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
pathology-streaming-pipeline
Use streaming to train whole-slides images with single image-level labels, by reducing GPU memory requirements with 99%.
3d-mri-brain-tumor-segmentation-using-autoencoder-regularization
Keras implementation of the paper "3D MRI brain tumor segmentation using autoencoder regularization" by Myronenko A. (https://arxiv.org/abs/1810.11654).
Mutual-Channel-Loss
Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)
pytorch-lightning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.