Regression

Regression models predict a numerical value associated with an input image within a certain predefined range.

Dataset format

Datasets follow this structure:

endpoint_url/bucket
├── prefix/images/
├── prefix/annotations.yaml
└── prefix/metadata.yaml

Dataset images are placed directly inside images/ (subdirectories are ignored).
The metadata file looks something like this:

task: regression
annotations: annotations.yaml
range: [-10, 8.7]

The annotations field specifies the name of the file containing the ground truth annotations.
Here's an example of annotations file:

000.jpg: 0.1
001.jpg: -4
002.jpg: 8.7
# ...