Pinned Repositories
Behavioral-Cloning
Cloning human driving behavior using a DNN
calamari
Line based ATR Engine based on OCRopy
Computer-Vision-Docker-Jupyter
Docker compose with custom DockerFile for Data Science and Computer Vision purpose
DeepLabCut
Markerless pose estimation of user-defined features with deep learning for all animals, including humans
docker_image
Docker Image for OCR4All, Larex and GTC
high-fidelity-generative-compression
Pytorch implementation of High-Fidelity Generative Image Compression + Routines for neural image compression
object-tracking
Tracking people in video
opencv
Open Source Computer Vision Library
Windy_Sentinel_Maps
Windy Sentinel Maps
yolov5
YOLOv5 in PyTorch > ONNX > CoreML > TFLite
Midnight93's Repositories
Midnight93/Computer-Vision-Docker-Jupyter
Docker compose with custom DockerFile for Data Science and Computer Vision purpose
Midnight93/bertlang
A web interface to understand language-specific BERT-models
Midnight93/bootstrap-italia-playground
Bootstrap Italia Playground
Midnight93/CI_CD
Midnight93/CLIP
Contrastive Language-Image Pretraining
Midnight93/covid-19-data
Data on COVID-19 (coronavirus) cases, deaths, hospitalizations, tests • All countries • Updated daily by Our World in Data
Midnight93/CTGAN
Conditional GAN for generating synthetic tabular data.
Midnight93/DeepEcho
Synthetic Data Generation for mixed-type, multivariate time series.
Midnight93/DeepSpeech-Italian-Model
Tooling for producing Italian model (public release available) for DeepSpeech and text corpus
Midnight93/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Midnight93/guida-api-istat
Guida all'uso delle API REST di ISTAT
Midnight93/kornia
Open Source Differentiable Computer Vision Library
Midnight93/kubernetes-the-hard-way
Bootstrap Kubernetes the hard way on Google Cloud Platform. No scripts.
Midnight93/Midnight93
profile presentation
Midnight93/momepy
Urban Morphology Measuring Toolkit
Midnight93/norfair
Lightweight Python library for adding real-time object tracking to any detector.
Midnight93/pytest-cov
Coverage plugin for pytest.
Midnight93/REST_API_Tutorial_Python
REST API Tutorial Python
Midnight93/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.
Midnight93/SDV
Synthetic Data Generation for tabular, relational and time series data.
Midnight93/spid-cie-oidc-django
The SPID/CIE OIDC Federation SDK, written in Python
Midnight93/Standard-Sim
StandardSim is a photorealistic synthetic dataset for retail environments
Midnight93/t81_558_deep_learning
Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks
Midnight93/textgrad
Textgrad - Forked
Midnight93/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.
Midnight93/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.
Midnight93/twinify
A software package for privacy-preserving generation of a synthetic twin to a given sensitive data set.
Midnight93/twitter-demographer
Midnight93/wikineural
Data and evaluation code for the paper WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER (EMNLP 2021).
Midnight93/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/