Modules Overview

Generators

medigan.generators Module

Base class providing user-library interaction methods for config management, and model selection and execution.

Classes

ConfigManager([config_dict, ...])

ConfigManager class: Downloads, loads and parses medigan's config json as dictionary.

DataLoader(dataset[, batch_size, shuffle, ...])

Data loader.

Dataset(*args, **kwds)

An abstract class representing a Dataset.

Generators([config_manager, model_selector, ...])

Generators class: Contains medigan's public methods to facilitate users' automated sample generation workflows.

ModelContributor(model_id, init_py_path)

ModelContributor class: Contributes a user's local model to the public medigan library

ModelExecutor(model_id, execution_config[, ...])

ModelExecutor class: Find config links to download models, init models as python packages, run generate methods.

ModelSelector([config_manager])

ModelSelector class: Given a config dict, gets, searches, and ranks matching models.

ModelVisualizer(model_executor, config)

ModelVisualizer class: Visualises synthetic data through a user interface.

SyntheticDataset(samples[, masks, ...])

A synthetic dataset containing data generated by a model of medigan

Utils()

Utils class containing reusable static methods.


ModelExecutor

medigan.execute_model.model_executor Module

Model executor class that downloads models, loads them as python packages, and runs their generate functions.

Classes

ModelExecutor(model_id, execution_config[, ...])

ModelExecutor class: Find config links to download models, init models as python packages, run generate methods.

Path(*args, **kwargs)

PurePath subclass that can make system calls.

Utils()

Utils class containing reusable static methods.

tqdm(*_, **__)

Decorate an iterable object, returning an iterator which acts exactly like the original iterable, but prints a dynamically updating progressbar every time a value is requested.


ModelVisualizer

medigan.model_visualizer Module

ModelVisualizer class providing visualizing corresponding model input and model output changes.

Classes

Button(ax, label[, image, color, hovercolor])

A GUI neutral button.

ModelVisualizer(model_executor, config)

ModelVisualizer class: Visualises synthetic data through a user interface.

Slider(ax, label, valmin, valmax[, valinit, ...])

A slider representing a floating point range.


ModelSelector

medigan.select_model.model_selector Module

Model selection class that describes, finds, compares, and ranks generative models.

Classes

ConfigManager([config_dict, ...])

ConfigManager class: Downloads, loads and parses medigan's config json as dictionary.

MatchedEntry(key, value[, matching_element])

MatchedEntry class: One target key-value pair that matches with a model's selection config.

ModelMatchCandidate(model_id, target_values)

ModelMatchCandidate class: A prospectively matching model given the target values as model search params.

ModelSelector([config_manager])

ModelSelector class: Given a config dict, gets, searches, and ranks matching models.

Utils()

Utils class containing reusable static methods.


ModelContributor

medigan.contribute_model.model_contributor Module

Model contributor class that tests models, creates metadata entries, uploads and contributes them to medigan.

Classes

GithubModelUploader(model_id, access_token)

GithubModelUploader class: Pushes the metadata of a user's model to the medigan repo, where it creates a dedicated github issue.

ModelContributor(model_id, init_py_path)

ModelContributor class: Contributes a user's local model to the public medigan library

Path(*args, **kwargs)

PurePath subclass that can make system calls.

Utils()

Utils class containing reusable static methods.

ZenodoModelUploader(model_id, access_token)

ZenodoModelUploader class: Uploads a user's model via API to Zenodo, here it is permanently stored with DOI.


ConfigManager

medigan.config_manager Module

Config manager class that downloads, ingests, parses, and prepares the config information for all models.

Classes

ConfigManager([config_dict, ...])

ConfigManager class: Downloads, loads and parses medigan's config json as dictionary.

Path(*args, **kwargs)

PurePath subclass that can make system calls.

Utils()

Utils class containing reusable static methods.