A new release of wai.annotations is out now: 0.7.3

This release includes:

• Upgraded wai.annotations.tf version from 1.1.0 to 1.2.0

• Included wai.annotations.voc (for Pascal VOC datasets)

A new release of wai.annotations is out: 0.7.1

The 0.7.x series saw a modularization happening behind the scenes, with each file format now being a separate repository and Python package. This makes it much easier to only include the relevant dependencies in ones virtual environment or docker image, keeping things as small as possible.

To further simplify the installation process, a docker-compose script has been compiled. This script now combines the Docker steps for setting up the PostgreSQL database, Redis and the actual backend.

Check out the updated Getting started page.

An experimental user interface for image classification is now available:

The interface is written in React and allows the user to incrementally improve their models until they are happy with the performance (human in the loop).

You can find out how to access this interface on the Getting started page.

In order to simplify the steps necessary to set up the backend, Docker images for the PostgreSQL database, the Redis server and the actual backend have been created. These images get rebuilt every night to always have the latest code-base available, making it easy to stay up-to-date.

Head over to the Getting started page and have a look.

A new Docker image for building models with version 0.4 of Detectron2 is available:

More information on the Docker image is available from Github:

github.com/waikato-datamining/pytorch/tree/master/detectron2/0.4

A new Docker image for building models with Detectron2 is available:

More information on the Docker image is available from Github:

github.com/waikato-datamining/pytorch/tree/master/detectron2