Skip to main content

Explainable AI, Model Monitoring, and Outlier Detection Tools for Computer Vision Systems

Project description

Obz AI 🔍: Explainable AI, Model Monitoring, and Outlier Detection for Computer Vision Systems

Obz AI is a powerful Python package designed to bring explainability, continuous monitoring, and advanced outlier detection to AI-powered computer vision systems. With support for the latest deep learning architectures -- including vision transformers (ViT) and convolutional neural networks (CNN) -- Obz AI enables ML practitioners and data scientists to ensure transparency, reliability, and trustworthiness in their vision models.

Obz AI offers seamless integration, allowing you to use its robust features as a standalone tool or connect effortlessly to the dashboard for real-time model monitoring, data visualization, and configuration. Track your machine learning models, visualize image data, generate XAI (Explainable AI) heatmaps, and perform anomaly detection.

For more details, demo, and full documentation, visit Obz.AI.

Key Features

  • Data Inspector Module: Automatically extracts features and detects outliers, data drifts, or other anomalies in image datasets using advanced statistical and machine learning methods — improving data quality and model robustness.
  • XAI Module: Generates state-of-the-art explainability heatmaps for computer vision models, including Saliency Maps, Attention Maps, CDAM, and more. Provides quantitative evaluation tools such as fidelity and compactness for model interpretability and explainability.
  • Obz Client: Effortlessly log and monitor your models, inputs, outputs, and XAI explanations to the Obz AI server (cloud or on-prem) for comprehensive oversight and user-friendly visualization.

Obz AI is the all-in-one solution for anyone building, deploying, or monitoring computer vision models -- empowering explainable, reliable, and secure AI applications.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

obzai-0.2.1.tar.gz (60.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

obzai-0.2.1-py3-none-any.whl (97.2 kB view details)

Uploaded Python 3

File details

Details for the file obzai-0.2.1.tar.gz.

File metadata

  • Download URL: obzai-0.2.1.tar.gz
  • Upload date:
  • Size: 60.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for obzai-0.2.1.tar.gz
Algorithm Hash digest
SHA256 9e92107ec78b5e415bd65ea969b98a915d9e44fa5a76e98e43c5da7cf6d92013
MD5 957dbc285ee8393a915747980ca69a9d
BLAKE2b-256 bdc95e51604ad9bbb8e045b72eda0d5edc4d66ab823a9ae967fb18543650c118

See more details on using hashes here.

Provenance

The following attestation bundles were made for obzai-0.2.1.tar.gz:

Publisher: release.yaml on alethia-xai/obzai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file obzai-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: obzai-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 97.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for obzai-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0cb61f6f970a4aa74916eb8680092f1fd8273377b721fa7da3e893277e651d13
MD5 f2af860ed902d6ec33869d5d191b91d9
BLAKE2b-256 9571fab5d11a2eb45c4346c96c14a92229e40a78bc39219adba9ff39c75565ba

See more details on using hashes here.

Provenance

The following attestation bundles were made for obzai-0.2.1-py3-none-any.whl:

Publisher: release.yaml on alethia-xai/obzai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page