Skip to content

TaskPaths

TaskPaths class

A TaskPaths object just provides paths to common directories that are used in different tasks, including NN training and inference. This paths are fixed because required directories are mounted as volume in Docker container.

class TaskPaths:
    def __init__(self, determine_in_project=True):

Create a TaskPaths object.

  • If determine_in_project is True, property project_dir will be set to path to (single) project in data_dir.

Properties

settings_path

Path to json file with input task settings.

model_dir

Path to NN model (checkpoint), i.e. directory with stored model weights. It is a model:

  • to apply it — for NN inference task

  • to continue training since it or to copy weights from it — for NN training task

Content of the directory is entirely dependent on model implementation.

results_dir

Path to directory where task results must be stored. It will be:

  • project in Supervisely format (possibly without images, with annotations only) — for NN inference task

  • directories with checkpoints — for NN training task

project_dir

Path to input project in Supervisely format. It will be:

  • data to apply NN model on it — for NN inference task

  • training data — for NN training task

debug_dir

Path to directory where some additional (debug) data may be stored. It may be useful for running tasks locally while developing (implementing NNs or something else).