Name: Andrea Ranieri
Type: User
Company: National Research Council of Italy (CNR)
Bio: Deep learning researcher @ CNR-IMATI. If you have a problem, if no one else can help, if your network doesn't learn...
Twitter: 4ndr3aR
Andrea Ranieri's Projects
Starter app for fastai v3 model deployment on Render
Let us control diffusion models!
Standalone repository of the CSRT tracker (the best performing real-time tracker in VOT2017 challenge, also known as CSRDCF++). This is a standalone build, aimed at ROS Kinetic users (opencv-3.3.1-dev).
Test data for DALI project
Unity project with an example on how to run the depthai library in Android.
CMake C++ example project using depthai library
DepthAI Python Library
Metadata specification for the DIGITbrain project
Unreal Engine plugin for easy creation of synthetic image datasets
The dataset consists of 600 images about pavement cracks taken from roads in Edmonton Canada. They are all annotated at pixel level for crack detection
The fastai deep learning library
Python supercharged for the fastai library
Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!
A jekyll theme inspired by linux consoles for hackers, developers and script kiddies.
A simple demo program for using OpenCV on Android
License plate generator - generates images of automobile license plates, similar to Italian plates
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
free-to-use landing-zone detection for UAV using DNNs for object segmentation. Now accepting SAFEs at 35M$ cap.
Code base of ParSeNet: ECCV 2020.
Implementaion of Auto Encoder in Pytorch
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
Online presentation for GitHub Pages and Jekyll in Markdown using reveal.js with a Solarized Color Theme
The project uses Unet-based improved networks to study road crack segmentation, which is based on keras.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.