Docker-Compose for Backend

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.

HTML Frontend for image classification

An experimental user interface for image classification is now available:

../../images/html_frontend_202104.thumbnail.png

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.

Docker for backend

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.

PyTorch image classification available

Today, a new library for performing image classification has made its debut:

wai.pytorchimageclass

The library is based on the PyTorch example code for imagenet. For ResNet-based networks, you can finetune pretrained models on your own data rather than just using the imagenet dataset. In addition, you can make predictions (single and batch/continuous), output information on built models, export trained models to TorchScript.

The library is also available via Docker images, one for GPU-based machines and one for CPU-only ones. However, the latter one should only be used for inference and not training, as it is simply too slow.

More information on the library and the Docker images is available from Github:

github.com/waikato-datamining/pytorch/tree/master/image-classification

wai.annotations release 0.5.4

A new release of wai.annotations is out now: 0.5.4

The introduction of image segmentation required more refactoring behind the scenes, which resulted in the 0.5.x release series.

Highlights since the 0.4.0 release:

  • MS COCO format can specify now labels to expect (in case subsets of the dataset do not have all labels present)

  • MS COCO format can now sort the determined labels to avoid ordering issues

  • MS COCO can write the discovered labels to a text file (comma-separated list)

  • Readers/writers no longer assume disk access

  • Macro support for simple command-line substitution

  • New image classification formats: subdir (used by Tensorflow image classification) and ADAMS (label of image present in report)

  • MS COCO/ROI/VGG object detection formats no longer write negative annotations

  • With the strip-annotations plugin, all annotations can be stripped during the conversion (e.g., for generating a dataset only consisting of images)

  • Image segmentation support: PNG with indexed palette for labels, PNG using blue channel for labels, layer-segments format which separates each label into a separate PNG (makes it easier to create subsets of labels)

Paper accepted

Our publication, A comparison of machine learning methods for cross-domain few-shot learning, has been accepted in the 33rd Australasian Joint Conference on Artificial Intelligence, Canberra, Australia.

For more details and downloads, see our publications page.