Since the 0.7.3 release, the following changes occurred:
Added wai.annotations.imgaug for performing image augmentations on the image stream (crop, flip, blur, grayscale, contrast, rotate, scale, )
Added wai.annotations.imgstats for generating label distributions
Added wai.annotations.imgvis for adding annotation overlays, viewing images, combining annotations into single overlay image
Added wai.annotations.redis.predictions for making predictions via a Redis backend (e.g., image classification, object detection, image segmentation)
Added wai.annotations.video for reading frames from video files/webcams, dropping frames, skipping similar frames, writing video files
Added wai.annotations.yolo for reading/writing [YOLO txt files](https://github.com/waikato-ufdl/wai-annotations-yolo/issues/1)
Upgraded wai.annotations.core version, adding ISP for discarding polygons, I/O support for images (with empty annotations)
Upgraded wai.annotations.tf version to support tensorflow 2.7.x
On top of that, the documentation available through ufdl.cms.waikato.ac.nz/wai-annotations-manual has been overhauled and the example section expanded to include examples for some of the new modules/plugins.
From now on, releases will be made available as Docker images under the following :
Finally, a working example of using a pretrained Yolov5 network to annotated (and visualize) frames extracted from a dashcam video can be found in the example section.