src.classification package

Subpackages

• src.classification.fusion package
  • Submodules
  • src.classification.fusion.fusion_classifier module
  • Module contents
• src.classification.image package
  • Submodules
  • src.classification.image.cross_attention_classifier module
  • src.classification.image.efficientnet_classifier module
  • src.classification.image.image_emotion_classifier module
  • src.classification.image.vgg16_classifier module
  • Module contents
• src.classification.plant package
  • Submodules
  • src.classification.plant.dense_classifier module
  • src.classification.plant.lstm_classifier module
  • src.classification.plant.mfcc_cnn_classifier module
  • src.classification.plant.mfcc_resnet_classifier module
  • src.classification.plant.nn_classifier module
  • src.classification.plant.plant_emotion_classifier module
  • Module contents
• src.classification.speech package
  • Submodules
  • src.classification.speech.byols_classifier module
  • src.classification.speech.gmm_classifier module
  • src.classification.speech.hmm_classifier module
  • src.classification.speech.hubert_classifier module
  • src.classification.speech.mfcc_lstm_classifier module
  • src.classification.speech.speech_emotion_classifier module
  • src.classification.speech.svm_classifier module
  • src.classification.speech.wav2vec2_classifier module
  • Module contents
• src.classification.text package
  • Submodules
  • src.classification.text.bert_classifier module
  • src.classification.text.distilbert_classifier module
  • src.classification.text.nrclex_classifier module
  • src.classification.text.text_emotion_classifier module
  • Module contents
• src.classification.watch package
  • Submodules
  • src.classification.watch.dense_classifier module
  • src.classification.watch.lstm_classifier module
  • src.classification.watch.nn_classifier module
  • src.classification.watch.random_forest_classifier module
  • src.classification.watch.transformer_classifier module
  • src.classification.watch.watch_emotion_classifier module
  • src.classification.watch.xgboost_classifier module
  • Module contents

Submodules

src.classification.classifier_factory module

src.classification.emotion_classifier module

Implement an emotion classifier base class

class src.classification.emotion_classifier.EmotionClassifier(name: str = 'base', data_type: Optional[str] = None, parameters: Optional[Dict] = None)

Bases: ABC

This class is the base class for all emotion classifiers

abstract classify(parameters: Dict, **kwargs) → array

The virtual classification method for interfacing

Parameters:

• parameters – Parameter dictionary used for classification

• kwargs – Additional kwargs parameters

Returns:

An array with predicted emotion indices

get_class_weights(which_set: Set, parameters: Optional[Dict] = None) → Dict[int, int]

Function that returns a class weights dictionary for a given dataset. The dictionary’s keys are the labels and the values are the counts.

Parameters:

• which_set – Which set to use for calculating the class weights.

• parameters – Parameter dictionary

Returns:

Dictionary with the class weights

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

Function that merges the parameters and kwargs

Parameters:

• parameters – Parameter dictionary

• kwargs – Additional parameters in kwargs

Returns:

Combined dictionary with parameters

abstract 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

abstract 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

abstract train(parameters: Dict, **kwargs) → None

The virtual training method for interfacing

Parameters:

• parameters – Parameter dictionary used for training

• kwargs – Additional kwargs parameters

Module contents

Package responsible for emotion classification