Midnight93

Computer-Vision-Docker-Jupyter

Docker compose with custom DockerFile for Data Science and Computer Vision purpose

bertlang

A web interface to understand language-specific BERT-models

bootstrap-italia-playground

Bootstrap Italia Playground

CI_CD

CLIP

Contrastive Language-Image Pretraining

covid-19-data

Data on COVID-19 (coronavirus) cases, deaths, hospitalizations, tests • All countries • Updated daily by Our World in Data

CTGAN

Conditional GAN for generating synthetic tabular data.

DeepEcho

Synthetic Data Generation for mixed-type, multivariate time series.

DeepSpeech-Italian-Model

Tooling for producing Italian model (public release available) for DeepSpeech and text corpus

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

guida-api-istat

Guida all'uso delle API REST di ISTAT

kornia

Open Source Differentiable Computer Vision Library

kubernetes-the-hard-way

Bootstrap Kubernetes the hard way on Google Cloud Platform. No scripts.

Midnight93

profile presentation

momepy

Urban Morphology Measuring Toolkit

norfair

Lightweight Python library for adding real-time object tracking to any detector.

pytest-cov

Coverage plugin for pytest.

repo_test_valohai

REST_API_Tutorial_Python

REST API Tutorial Python

Restormer

Official repository for "Restormer: Efficient Transformer for High-Resolution Image Restoration". SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

SDV

Synthetic Data Generation for tabular, relational and time series data.

spid-cie-oidc-django

The SPID/CIE OIDC Federation SDK, written in Python

Standard-Sim

StandardSim is a photorealistic synthetic dataset for retail environments

t81_558_deep_learning

Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks

TOG_Champagne

Real-time object detection is one of the key applications of deep neural networks (DNNs) for real-world mission-critical systems. While DNN-powered object detection systems celebrate many life-enriching opportunities, they also open doors for misuse and abuse. This project presents a suite of adversarial objectness gradient attacks, coined as TOG, which can cause the state-of-the-art deep object detection networks to suffer from untargeted random attacks or even targeted attacks with three types of specificity: (1) object-vanishing, (2) object-fabrication, and (3) object-mislabeling. Apart from tailoring an adversarial perturbation for each input image, we further demonstrate TOG as a universal attack, which trains a single adversarial perturbation that can be generalized to effectively craft an unseen input with a negligible attack time cost. Also, we apply TOG as an adversarial patch attack, a form of physical attacks, showing its ability to optimize a visually confined patch filled with malicious patterns, deceiving well-trained object detectors to misbehave purposefully.

Trendr_App

Twitter Trends history explorer app. Trending topics can be explored by date and location. Backend served with Lambda Function (NodeJS) from AWS. Frontend made with VueJS. Twitter API queried with a Python script from Google Colab. MongoDB database.

twinify

A software package for privacy-preserving generation of a synthetic twin to a given sensitive data set.

twitter-demographer

wikineural

Data and evaluation code for the paper WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER (EMNLP 2021).

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/