<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/neural-structured-learning/blob/v1.4.0/neural_structured_learning/configs/__init__.py) |

Configuration classes and APIs for Neural Structured Learning.

## Classes

[`class AdvNeighborConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/AdvNeighborConfig): Contains configuration for generating adversarial neighbors.

[`class AdvRegConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/AdvRegConfig): Contains configuration for adversarial regularization.

[`class AdvTargetConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/AdvTargetConfig): Contains configuration for selecting targets to be attacked.

[`class AdvTargetType`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/AdvTargetType): Types of adversarial targeting.

[`class DecayConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/DecayConfig): Contains configuration for decaying a value during training.

[`class DecayType`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/DecayType): Types of decay.

[`class DistanceConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/DistanceConfig): Contains configuration for computing distances between tensors.

[`class DistanceType`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/DistanceType): Types of distance.

[`class GraphBuilderConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/GraphBuilderConfig): Encapsulates configuration parameters for building a graph.

[`class GraphNeighborConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/GraphNeighborConfig): Specifies neighbor attributes for graph regularization.

[`class GraphRegConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/GraphRegConfig): Contains the configuration for graph regularization.

[`class IntegrationConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/IntegrationConfig): Contains configuration for computing multimodal integration.

[`class IntegrationType`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/IntegrationType): Types of integration for multimodal fusion.

[`class NormType`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/NormType): Types of norms.

[`class TransformType`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/TransformType): Types of nonlinear functions to be applied .

[`class VirtualAdvConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/VirtualAdvConfig): Contains configuration for virtual adversarial training.

## Functions

[`make_adv_reg_config(...)`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/make_adv_reg_config): Creates an [`nsl.configs.AdvRegConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/AdvRegConfig) object.

[`make_graph_reg_config(...)`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/make_graph_reg_config): Creates an [`nsl.configs.GraphRegConfig`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/configs/GraphRegConfig) object.

<br />

<br />

<br />

| ## Other Members ||
|---|---|
| DEFAULT_ADVERSARIAL_PARAMS | <br /> { 'adv_grad_norm': <NormType.L2: 'l2'>, 'adv_step_size': 0.001, 'clip_value_max': None, 'clip_value_min': None, 'feature_mask': None, 'pgd_epsilon': None, 'pgd_iterations': 1, 'random_init': False } <br /> |
| DEFAULT_DISTANCE_PARAMS | <br /> { 'distance_type': <DistanceType.L2: 'l2'>, 'reduction': 'weighted_sum_by_nonzero_weights', 'sum_over_axis': None, 'transform_fn': <TransformType.NONE: 'none'> } <br /> |

<br />