Skip to content
View damianozappia's full-sized avatar
0 followers · 1 following

Block or report damianozappia

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
damianozappia/README.md
LinkedIn Badge Twitter Badge

👨‍💻 About Me :

  • 👋 Hi, I’m @damianozappia
  • 👀 I’m interested in AI, Robotics, tech stuff in general
  • 🌱 I’m currently learning lot of cool stuff related to Python, Pytorch, Machine Learning, Deep Learning, Computer Vision and so on...
  • 📫 How to reach me: mail to [email protected]

💻 My Projects Portfolio :

An Adversarial Approach to Improve Instance Segmentation in Automotive

  • The purpose of this work was to demonstrate how Instance Segmentation can be further improved allowing (in an autonomous driving context) the vehicle to count on a strong and reliable algorithm, that can help into choosing the right action while driving. The Instance Segmentation network is paired with a Generative Adversarial Network, using an Adversarial Approach framework, where the two networks are forced to compete and thus to improve each other.
  • https://github.com/damianozappia/Master-s-Thesis

The use of Keras Retinanet on the AVA dataset

  • The aim of the project was to implement and utilize the Keras RetinaNet, a one stage object detector that analysing images is capable of recognising objects, actions etc inside them. The RetinaNet has been used first with one of the default public datasets available for objects classification (Pascal VOC), and then with the AVA dataset, to classify actions inside pictures.
  • https://github.com/damianozappia/ElectiveInAI-Module1-project

Eagle Flight - Graphical Application developed for Interactive Graphics course

Generative Adversarial Network for the creation of anime faces

  • The aim was to build a GAN able to generate from scratch faces of anime, with the ability to overcome the non convergence problems that raise at resolution higher than 64x64 pixels, and adopting strategies that allowed the generation of 128x128 pixels images, with a good level of detail and realism.
  • https://github.com/damianozappia/AnimeFaces_GAN

Derivation of Kinematic Equations for KUKA youBot with "Pick and Place” implementation

  • The aim of this project has been to develop a software using python and ROS (Robot Operating System), that had the purpose of computing the inverse kinematics for the KUKA YouBot, and use it to perform a pick and place manipulation task, picking an object in a given position and placing it in another specified position on the robot's base.
  • https://gitlab.com/damianozappia/kuka-youbot-manipulator/-/tree/master/

Popular repositories Loading

  1. HRI_Project HRI_Project Public

    HRI Project - Elective in AI

    Python 1

  2. AnimeFaces_GAN AnimeFaces_GAN Public

    Generative Adversarial Network for the creation of anime faces

    Jupyter Notebook 1

  3. ElectiveInAI-Module1-project ElectiveInAI-Module1-project Public

    Project folder for Elective in AI 1, held by prof Pirri at Sapienza Università di Roma

    Jupyter Notebook

  4. Master-s-Thesis Master-s-Thesis Public

    An adversarial approach to improve instance segmentation in automotive - Master's Thesis

    Jupyter Notebook

  5. deeplab-pytorch deeplab-pytorch Public

    Forked from kazuto1011/deeplab-pytorch

    PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC

    Python

  6. streamlit_trial streamlit_trial Public

    Python