It's not just a linter that annoys you!

Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)

PyTorch-centric library for evaluating and enhancing the robustness of AI technologies

ARMORY Adversarial Robustness Evaluation Test Bed

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-…

Demonstration Web UI to visualize XAITK Saliency functionality.

Research Artifact of ICSE 2023 Paper: Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion

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

Making Docker and Kubernetes management easy.

Web service(s) pertaining to functionality exposed by the xaitk-saliency package.

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

A data augmentations library for audio, image, text, and video.

Interpretability and explainability of data and machine learning models

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.

Privacy Testing for Deep Learning

A JupyterLab extension for displaying dashboards of GPU usage.

An awesome list of papers on privacy attacks against machine learning

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.

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 mode…

A collection of infrastructure and tools for research in neural network interpretability.

飞桨可信AI

`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.

Code release of a paper "Guiding Deep Learning System Testing using Surprise Adequacy"

An open source, Explainable AI (XAI) framework and toolkit for visual saliency algorithm interfaces and implementations, built for analytics and autonomy applications.

OpenMMLab Image Classification Toolbox and Benchmark

OpenMMLab Detection Toolbox and Benchmark

OpenMMLab Computer Vision Foundation