v1.6.8

• Improved multi-thread support for ONNX on .NET
• improved image handling for MacOS/Linux
• Added support for sideloading modules
• Better arm64 support
• General cleanups

v1.6.0.0

• Optimised RAM use
• Ability to enable / disable modules and GPU support via the dashboard
• REST settings API for updating settings on the fly
• Apple M1/M2 GPU support
• Async processes and logging for a performance boost
• Breaking: the CustomObjectDetection is now part of ObjectDetectionYolo

v1.5.6.2

• Docker nVidia GPU support
• Further performance improvements
• cuDNN install script to help with nVidia driver and toolkit installation
• Bug fixes

v1.5.6

• nVidia GPU support!
• Perf improvements to Python modules
• Work on the Python SDK to make creating modules easier
• Dev installers now drastically simplified for those creating new modules
• Added SuperResolution as a demo module

v1.5.5

• Some minor cleanups to python SDK in prep for serious refactoring
• endless fights with Windows Installer XML that has resulted in a few nips and tucks
• Benchmark now allows any custom model you choose
• Overriding settings for some legacy modules now far easier: Blue Iris users will benefit
• Front end Server is now a self-contained .NET package

v1.5.1

A small patch to correct an installer issue

v1.5.0

• Added Custom model support
• Cleaned out Installer folder
• Rebrand from CodeProject senseAI to CodeProject.AI

v1.4.0

• Updated the module system module definitions to provide automated documentation
• New module: Sentiment analysis
• Revamped dashboard and senseAI Explorer
• Updated docker

v1.3.0

• Reworked the module system in order to better encapsulate module definitions
• Two new modules: Portrait mode and Remove Background
• Support for multiple versions of Python
• Updated docker
• Reorganized / refactored dev environment setup scripts to make it easier to add new modules

Full Changelog: https://github.com/codeproject/CodeProject.SenseAI/commits/v1.3.0