Name: Björn Barz
Type: User
Company: Carl Zeiss AG, Corporate Research & Technology
Bio: Machine Learning Scientist at Carl Zeiss AG, Corporate Research and Technology.
Previously: PostDoc at University of Jena (Germany), Computer Vision Group.
Twitter: Callidior
Location: Jena, Germany
Björn Barz's Projects
Caffe: a fast open framework for deep learning.
ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection
Reference implementations of popular deep learning models.
Keras package for deep residual networks
Keras library for building (Universal) Transformers, facilitating BERT and GPT models
Efficient C/C++ implementation of Information-Theoretic Metric Learning (ITML)
Metric learning algorithms in Python
Machine learning metrics for distributed, scalable PyTorch applications.
Predict paper titles from abstracts using a BERT2BERT transformer model.
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
Set of tools for Roundcube webmail
(CVPR 2022) Pytorch implementation of "Self-supervised transformers for unsupervised object discovery using normalized cut"