xzhewei
Hi, I am an artificial intelligence researcher, and my research direction is Trustworthy & Responsible AI.
NoneChina
Pinned Repositories
AdvBox
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.
adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
AIX360
Interpretability and explainability of data and machine learning models
Colorimetry
darknet-for-SCUT
Yolo for pedestrian detection task.
datatool
SCUT FIR Pedestrian Dataset data toolbox
pydatatool
Pedestrian detection python tool for Detectron framework
TFRCN
Thermal Faster R-CNN for FIR Pedestrians Detection on SCUT Dataset
toolbox
Piotr's Image & Video Matlab Toolbox
xzhewei's Repositories
xzhewei/AdvBox
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.
xzhewei/adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
xzhewei/AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
xzhewei/AIX360
Interpretability and explainability of data and machine learning models
xzhewei/armory
ARMORY Adversarial Robustness Evaluation Test Bed
xzhewei/AugLy
A data augmentations library for audio, image, text, and video.
xzhewei/awesome-ml-privacy-attacks
An awesome list of papers on privacy attacks against machine learning
xzhewei/cube-studio
cube studio开源云原生一站式机器学习平台,支持sso登录,多租户/多项目组,数据资产对接,notebook在线开发,拖拉拽任务流pipeline编排,多机多卡分布式训练,超参搜索,推理服务VGPU,多集群调度,边缘计算,serverless,标注平台,自动化标注,数据集管理,大模型实时训练,llmops,私有知识库,AI应用商店,支持模型一键开发/推理/微调,私有化部署,支持国产芯片
xzhewei/Deephunter-backup
xzhewei/dslinter
`dslinter` is a pylint plugin for linting data science and machine learning code. We plan to support the following Python libraries: TensorFlow, PyTorch, Scikit-Learn, Pandas and NumPy.
xzhewei/evals
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
xzhewei/hoppscotch
Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)
xzhewei/jupyterlab-nvdashboard
A JupyterLab extension for displaying dashboards of GPU usage.
xzhewei/lucid
A collection of infrastructure and tools for research in neural network interpretability.
xzhewei/ml_privacy_meter
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
xzhewei/mmclassification
OpenMMLab Image Classification Toolbox and Benchmark
xzhewei/mmcv
OpenMMLab Computer Vision Foundation
xzhewei/mmdetection
OpenMMLab Detection Toolbox and Benchmark
xzhewei/NeuraL-Coverage
Research Artifact of ICSE 2023 Paper: Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion
xzhewei/portainer
Making Docker and Kubernetes management easy.
xzhewei/PrivacyRaven
Privacy Testing for Deep Learning
xzhewei/pylint
It's not just a linter that annoys you!
xzhewei/responsible-ai-toolbox
PyTorch-centric library for evaluating and enhancing the robustness of AI technologies
xzhewei/sadl
Code release of a paper "Guiding Deep Learning System Testing using Surprise Adequacy"
xzhewei/TrustAI-Paddle
飞桨可信AI
xzhewei/visualblocks
Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-and-drop ML components, including models, user inputs, processors, and visualizations.
xzhewei/xaitk-saliency
An open source, Explainable AI (XAI) framework and toolkit for visual saliency algorithm interfaces and implementations, built for analytics and autonomy applications.
xzhewei/xaitk-saliency-web-api
Web service(s) pertaining to functionality exposed by the xaitk-saliency package.
xzhewei/xaitk-saliency-web-demo
Demonstration Web UI to visualize XAITK Saliency functionality.
xzhewei/xzhewei.github.io