daniel-unyi-42
Data Science & Deep Learning Specialist PhD Student at Budapest University of Technology and Economics
Pinned Repositories
ARAP-Python
Simple and fast as-rigid-as-possible registration in Python (using Scipy and Trimesh) based on the paper by Olga Sorkine and Marc Alexa.
Cortex-SSL
dHCP
developing Human Connectome Project
Equivariant-Cortical-Mesh-Segmentation
Source code for our paper "Utility of Equivariant Message Passing in Cortical Mesh Segmentation" (MIUA 2022)
GALA
GC-VAE
GWNN-TensorFlow-2-implementation
Easy-to-use Graph Wavelet Neural Network in a single .py file
Neurodevelopmental-Phenotype-Prediction
pytorch_geometric
Graph Neural Network Library for PyTorch
thesis
My thesis: Graph Convolutional Neural Networks and Applications
daniel-unyi-42's Repositories
daniel-unyi-42/GWNN-TensorFlow-2-implementation
Easy-to-use Graph Wavelet Neural Network in a single .py file
daniel-unyi-42/Neurodevelopmental-Phenotype-Prediction
daniel-unyi-42/GALA
daniel-unyi-42/GC-VAE
daniel-unyi-42/pytorch_geometric
Graph Neural Network Library for PyTorch
daniel-unyi-42/thesis
My thesis: Graph Convolutional Neural Networks and Applications
daniel-unyi-42/ARAP-Python
Simple and fast as-rigid-as-possible registration in Python (using Scipy and Trimesh) based on the paper by Olga Sorkine and Marc Alexa.
daniel-unyi-42/Cortex-SSL
daniel-unyi-42/dHCP
developing Human Connectome Project
daniel-unyi-42/Equivariant-Cortical-Mesh-Segmentation
Source code for our paper "Utility of Equivariant Message Passing in Cortical Mesh Segmentation" (MIUA 2022)
daniel-unyi-42/GStarX
daniel-unyi-42/Laplacian2Mesh
Laplacian2Mesh: Laplacian-Based Mesh Understanding
daniel-unyi-42/INNOSE-dev
daniel-unyi-42/metalearning
daniel-unyi-42/MICCAI-2022-SLCN-solution
daniel-unyi-42/mlops_mobile_price_predictor
daniel-unyi-42/MTO-production
Mestry model for make-to-order production planning, implemented with PuLP
daniel-unyi-42/pytorch_cluster
PyTorch Extension Library of Optimized Graph Cluster Algorithms
daniel-unyi-42/segger_dev
a cutting-edge cell segmentation model specifically designed for single-molecule resolved spatial omics datasets. It addresses the challenge of accurately segmenting individual cells in complex imaging datasets, leveraging a unique approach based on graph neural networks (GNNs).