nicetoolbox.detectors.method_detectors.base_detector.BaseDetector

class nicetoolbox.detectors.method_detectors.base_detector.BaseDetector(config, io, data, requires_out_folder=True)

Bases: ABC

Abstract class to setup and run existing computer vision research code, called method detectors.

components

A list of components associated with the method detector.

Type:

list

algorithm

The algorithm used for detecting the component.

Type:

str

out_folder

The output folder.

Type:

str

viz_folder

The visualization folder.

Type:

str

subjects_descr

The subjects description.

Type:

str

config_path

The path to the configuration file.

Type:

str

conda_path

The path to the conda installation.

Type:

str

framework

The name of the framework used for the method detector.

Type:

str

script_path

The path to the script used for the method detector.

Type:

str

venv

The type of virtual environment used for the method detector.

Type:

str

env_name

The name of the virtual environment used for the method detector.

Type:

str

venv_path

The path to the virtual environment used for the method detector.

Type:

str

Sets up the input and output folders required for each method based on the provided configurations. Saves a copy of the configuration file for the method detector.

Parameters:

• config (dict) – Configuration parameters for the detector.

• io (IO) – An instance of the IO class for input/output operations.

• data (Data) – An instance of the Data class for accessing data.

• requires_out_folder (bool, optional) – Indicates whether an output folder is required. Defaults to True.

Methods

post_inference	Post-processing after inference.
run_inference	Runs the inference of the method detector in a separate terminal/cmd window using the specified virtual environment or conda environment.
visualization	Abstract method to visualize the output of the method, preferably as a video.

Attributes

algorithm	Abstract property that returns the algorithm of the method detector.
components	Abstract property that returns the components of the method detector.

abstract property algorithm: str

Abstract property that returns the algorithm of the method detector.

This property should be implemented in the derived classes to specify the algorithm that the method detector is associated with.

Returns:

A string representing the algorithm associated with the method detector

Return type:

str

Raises:

NotImplementedError – If the property is not set in the derived classes.

abstract property components: list[str]

Abstract property that returns the components of the method detector.

This property should be implemented in the derived classes to specify the components that the method detector is associated with.

Returns:

A list of strings representing the components associated with the

method detector.

Return type:

list

Raises:

NotImplementedError – If the property is not set in the derived classes.

abstract post_inference() → None

Post-processing after inference.

This method is called after the inference step and is used for any post-processing tasks that need to be performed.

run_inference() → None

Runs the inference of the method detector in a separate terminal/cmd window using the specified virtual environment or conda environment. Captures the output and logs the success or failure of the inference.

abstract visualization(data) → None

Abstract method to visualize the output of the method, preferably as a video.

This method is intended to generate a visual representation of the method detector’s output. The visualization should be saved in the self.viz_folder.

Parameters:

data (any) – The data to be visualized. The type and content of this parameter depend on the specific implementation of the method detector.

Returns:

None. This method does not return any value. However, it should save the

visualization in the self.viz_folder.

Raises:

NotImplementedError – If this method is not implemented in the derived classes.