stouputils.data_science.models.keras.convnext module#

ConvNeXt models implementation.

This module provides wrapper classes for the ConvNeXt family of models from the Keras applications. ConvNeXt models are a family of pure convolutional networks that match or outperform Vision Transformers (ViTs) while maintaining the simplicity and efficiency of CNNs.

Available models:

  • ConvNeXtTiny: Smallest variant with fewer parameters for resource-constrained environments

  • ConvNeXtSmall: Compact model balancing performance and size

  • ConvNeXtBase: Standard model with good performance for general use cases

  • ConvNeXtLarge: Larger model with higher capacity for complex tasks

  • ConvNeXtXLarge: Largest variant with maximum capacity for demanding applications

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

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

Bases: BaseKeras

ConvNeXtTiny 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 ConvNeXtTiny 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:

ConvNeXtTiny

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

Bases: BaseKeras

ConvNeXtSmall 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 ConvNeXtSmall 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:

ConvNeXtSmall

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

Bases: BaseKeras

ConvNeXtBase 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 ConvNeXtBase 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:

ConvNeXtBase

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

Bases: BaseKeras

ConvNeXtLarge 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 ConvNeXtLarge 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:

ConvNeXtLarge

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

Bases: BaseKeras

ConvNeXtXLarge 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 ConvNeXtXLarge 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:

ConvNeXtXLarge

model#

alias of ConvNeXtXLarge