stouputils.data_science.models.keras.densenet module#

DenseNet models implementation.

This module provides wrapper classes for the DenseNet family of models from the Keras applications. DenseNet models utilize dense connections between layers, where each layer obtains additional inputs from all preceding layers and passes on its feature-maps to all subsequent layers.

Available models:

  • DenseNet121: Smallest variant with 121 layers

  • DenseNet169: Medium-sized variant with 169 layers

  • DenseNet201: Largest variant with 201 layers

All models support transfer learning from ImageNet pre-trained weights.

class DenseNet121(num_classes: int, kfold: int = 0, transfer_learning: str = 'imagenet', **override_params: Any)[source]#

Bases: BaseKeras

DenseNet121 implementation using advanced model class with common functionality. For information, refer to the ModelInterface class.

class_routine(kfold: int = 0, transfer_learning: str = 'imagenet', verbose: int = 0, **override_params: Any) → ModelInterface#

Run the full routine for DenseNet121 model.

Parameters:

  • dataset (Dataset) – Dataset to use for training and evaluation.

  • kfold (int) – K-fold cross validation index.

  • transfer_learning (str) – Pre-trained weights to use, can be “imagenet” or a dataset path like ‘data/pizza_not_pizza’.

  • verbose (int) – Verbosity level.

  • **kwargs (Any) – Additional arguments.

Returns:

Trained model instance.

Return type:

DenseNet121

class DenseNet169(num_classes: int, kfold: int = 0, transfer_learning: str = 'imagenet', **override_params: Any)[source]#

Bases: BaseKeras

DenseNet169 implementation using advanced model class with common functionality. For information, refer to the ModelInterface class.

class_routine(kfold: int = 0, transfer_learning: str = 'imagenet', verbose: int = 0, **override_params: Any) → ModelInterface#

Run the full routine for DenseNet169 model.

Parameters:

  • dataset (Dataset) – Dataset to use for training and evaluation.

  • kfold (int) – K-fold cross validation index.

  • transfer_learning (str) – Pre-trained weights to use, can be “imagenet” or a dataset path like ‘data/pizza_not_pizza’.

  • verbose (int) – Verbosity level.

  • **kwargs (Any) – Additional arguments.

Returns:

Trained model instance.

Return type:

DenseNet169

class DenseNet201(num_classes: int, kfold: int = 0, transfer_learning: str = 'imagenet', **override_params: Any)[source]#

Bases: BaseKeras

DenseNet201 implementation using advanced model class with common functionality. For information, refer to the ModelInterface class.

class_routine(kfold: int = 0, transfer_learning: str = 'imagenet', verbose: int = 0, **override_params: Any) → ModelInterface#

Run the full routine for DenseNet201 model.

Parameters:

  • dataset (Dataset) – Dataset to use for training and evaluation.

  • kfold (int) – K-fold cross validation index.

  • transfer_learning (str) – Pre-trained weights to use, can be “imagenet” or a dataset path like ‘data/pizza_not_pizza’.

  • verbose (int) – Verbosity level.

  • **kwargs (Any) – Additional arguments.

Returns:

Trained model instance.

Return type:

DenseNet201

model#

alias of DenseNet201