diplomat.processing

This module defines the abstract base class for predictor plugins, and additional data structures, classes, and functions used for processing network outputs into body part pose predictions.

Functions

get_predictor(name)	Get the predictor plugin by the specified name.
get_predictor_plugins()	Get and retrieve all predictor plugins currently available to the DeepLabCut implementation.

Classes

Predictor(bodyparts, num_outputs, ...)	Base plugin class for all predictor plugins.
TrackingData(scmap[, locref, stride])	Represents tracking data received from the DeepLabCut neural network.
ProgressBar([total])	Abstract API for representing a progress bar.
TQDMProgressBar([total, tqdm_prior])	A Concrete implementation of the ProgressBar API, uses TQDM to display progress.
Pose(x, y, prob)	Class defines the Poses for given amount of frames and body parts.
TypeCaster(*args, **kwds)	Protocol for a type casting method.
Config(*args, **kwargs)	Represents a configuration of settings.

Modules

diplomat.processing.containers	Provides the config container implementation, used for storing configuration parameters.
diplomat.processing.pose	Provides the Pose class, used for storing final predicted body part locations.
diplomat.processing.predictor
diplomat.processing.progress_bar	Provides an abstract progress bar interface that is passed to predictors for tracking progress.
diplomat.processing.track_data	Provides the TrackingData class, used for storing model outputs and passing them to predictors.
diplomat.processing.type_casters	Provides an interface and several types for performing automatic typecasting.