Documentation β’ Getting Started β’ Upload Model & Data β’ Blog β’ Discord Community β’ Advisors
Giskard creates interfaces for humans to inspect AI models. It is open-source & self-hosted.
β‘ Explore and Validate - Collaborate with business stakeholders with direct feedback & discussion.
π§βπ§ Test - Exhaustive test suites, backed by State-of-the-Art ML research.
π§βπ§ Automate - Protect your ML models against the risk of regressions, drift and bias.
Click the image below to start the demo:
![Interactive demo](/ManeSah/giskard/raw/7c9b17d9b44cbffb50aed1ae327064af55c243e8/readme/demo.png)
Requirements: git
, docker
and docker-compose
git clone https://github.com/Giskard-AI/giskard.git
cd giskard
docker-compose up -d
After the application is started you can access at:
http://localhost:19000 with default login / password: admin / admin
![Interactive demo](/ManeSah/giskard/raw/7c9b17d9b44cbffb50aed1ae327064af55c243e8/readme/upload.png)
Easy upload for any Python model: PyTorch, TensorFlow, Transformers, Scikit-learn, etc.
π Documentation
![Interactive demo](/ManeSah/giskard/raw/7c9b17d9b44cbffb50aed1ae327064af55c243e8/readme/feedback.png)
Improve ML models with business stakeholders in no time.
π Documentation
![Interactive demo](/ManeSah/giskard/raw/7c9b17d9b44cbffb50aed1ae327064af55c243e8/readme/test.png)
Exhaustive test suites, backed by β¨State-of-the-Art ML research.
π Documentation
![Deploy tests in CI/CD Pipeline](/ManeSah/giskard/raw/7c9b17d9b44cbffb50aed1ae327064af55c243e8/readme/pipeline.png)
Protect your ML models against the risk of regressions, drift and bias.
π Documentation
We welcome contributions from the Machine Learning community!
Read this guide to get started.