Pinned Repositories
doc2graph
Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.
dex-net
Repository for reading the Dex-Net 2.0 HDF5 database of 3D objects, parallel-jaw grasps, and robust grasp metrics
spectral_learning
Learning in spectral network space
adversarial_training_methods
Implementation of the methods proposed in **Adversarial Training Methods for Semi-Supervised Text Classification** on IMDB dataset (without pre-training)
encephalic_vasculature_mapping
This work aims to explore a new approach to model the encephalic vasculature using the formalism of graphs that naturally fit the structure of blood vessels.
growing_hierarchical_som
Self-Organizing Map [https://en.wikipedia.org/wiki/Self-organizing_map] is a popular method to perform cluster analysis. SOM shows two main limitations: fixed map size constraints how the data is being mapped and hierarchical relationships are not easily recognizable. Thus Growing Hierarchical SOM has been designed to overcome this issues
image_viewer
A simple image viewer capable of showing EXIF tags
RWVC-BDD100K
RWVC-BDD100K is a set of image-level annotations on road, weather and visibility condition for a large number of examples from the BDD100K dataset.
SEMI-FALKON
Falkon is one of the most efficient algorithm able to work in a supervised large scale setting. This method is the result of a combination of three simple principles: sub-sampling, preconditioning and iterative solvers. In order to extend FALKON usability we have designed an extension able to work in a semi-supervised scenario.
super_resolution
Super-resolution is a technique that constructs an high-resolution image from several observed low-resolution images.
enricivi's Repositories
enricivi/growing_hierarchical_som
Self-Organizing Map [https://en.wikipedia.org/wiki/Self-organizing_map] is a popular method to perform cluster analysis. SOM shows two main limitations: fixed map size constraints how the data is being mapped and hierarchical relationships are not easily recognizable. Thus Growing Hierarchical SOM has been designed to overcome this issues
enricivi/adversarial_training_methods
Implementation of the methods proposed in **Adversarial Training Methods for Semi-Supervised Text Classification** on IMDB dataset (without pre-training)
enricivi/super_resolution
Super-resolution is a technique that constructs an high-resolution image from several observed low-resolution images.
enricivi/image_viewer
A simple image viewer capable of showing EXIF tags
enricivi/encephalic_vasculature_mapping
This work aims to explore a new approach to model the encephalic vasculature using the formalism of graphs that naturally fit the structure of blood vessels.
enricivi/SEMI-FALKON
Falkon is one of the most efficient algorithm able to work in a supervised large scale setting. This method is the result of a combination of three simple principles: sub-sampling, preconditioning and iterative solvers. In order to extend FALKON usability we have designed an extension able to work in a semi-supervised scenario.
enricivi/RWVC-BDD100K
RWVC-BDD100K is a set of image-level annotations on road, weather and visibility condition for a large number of examples from the BDD100K dataset.
enricivi/enricivi.github.io
:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.