TaskHelperInference object contains useful things that are needed to run inference with NN as Supervisely task.
class TaskHelperInference: def __init__(self):
TaskPaths object with paths to input and output directories.
Task input settings (Python dictionary).
For inference task it is exactly config typed by user in web panel. The config should be a JSON object, but content of the config is entirely dependent on model implementation.
Meta (metadata) of input project. The meta contains, among others, list of project classes and is required to read annotations in Supervisely format now.