src.classification.fusion package

Submodules

src.classification.fusion.fusion_classifier module

This file contains a fusion emotion classifier fusing image, plant and watch probabilities

class src.classification.fusion.fusion_classifier.FusionClassifier(parameters: Optional[Dict] = None)

Bases: EmotionClassifier

Class that implements the fusion emotion classifier. This classifier performs early fusion from the following classifiers: image, plant and watch (they can be excluded or included). We take the seven emotion probabilities as features from the three classifiers and then classify this data. We do not take the real features that the classifiers extract as our input data.

To generate the data required to use this classifier, run the script: src/evaluation/scripts/continuous_data_creation.py

classify(parameters: Optional[Dict] = None, **kwargs) → array

Classification method used to classify emotions from images

Parameters:

• parameters – Parameter dictionary used for classification

• kwargs – Additional kwargs parameters

Returns:

An array with predicted emotion indices

initialize_model(parameters: Dict) → None

Initializes a new fusion model architecture

load(parameters: Optional[Dict] = None, **kwargs) → None

Loading method that loads a previously trained model from disk.

Parameters:

• parameters – Parameters required for loading the model

• kwargs – Additional kwargs parameters

prepare_training(parameters: Dict) → None

Function that prepares the training by initializing optimizer, loss, metrics and callbacks for training.

Parameters:

parameters – Training parameters

save(parameters: Optional[Dict] = None, **kwargs) → None

Saving method that saves a previously trained model on disk.

Parameters:

• parameters – Parameters required for storing the model

• kwargs – Additional kwargs parameters

train(parameters: Optional[Dict] = None, **kwargs) → None

Training method for Fusion model

Parameters:

• parameters – Parameter dictionary used for training

• kwargs – Additional kwargs parameters

Module contents

This package contains multi-modal and fusion emotion classifiers.