keras_config module

KerasConfig

class edgeimpulse_api.models.keras_config.KerasConfig(
		**data: Any
)

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Parameters

• **data: Any

Bases

• pydantic.main.BaseModel

• pydantic.utils.Representation

Class variables

• Config

• akida_edge_learning_config: Optional[edgeimpulse_api.models.akida_edge_learning_config.AkidaEdgeLearningConfig]

• anomaly_capacity: Optional[edgeimpulse_api.models.anomaly_capacity.AnomalyCapacity]

• augmentation_policy_image: edgeimpulse_api.models.augmentation_policy_image_enum.AugmentationPolicyImageEnum

• augmentation_policy_spectrogram: Optional[edgeimpulse_api.models.augmentation_policy_spectrogram.AugmentationPolicySpectrogram]

• auto_class_weights: Optional[pydantic.types.StrictBool]

• batch_size: Optional[pydantic.types.StrictInt]

• block_parameters: Optional[edgeimpulse_api.models.block_parameters.BlockParameters]

• custom_parameters: Optional[Dict[str, pydantic.types.StrictStr]]

• custom_validation_metadata_key: Optional[pydantic.types.StrictStr]

• default_batch_size: pydantic.types.StrictInt

• dependencies: edgeimpulse_api.models.dependency_data.DependencyData

• last_shown_model_engine: Optional[edgeimpulse_api.models.model_engine_short_enum.ModelEngineShortEnum]

• last_shown_model_variant: Optional[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum]

• learning_rate: float

• minimum_confidence_rating: float

• mode: pydantic.types.StrictStr

• name: pydantic.types.StrictStr

• profile_int8: pydantic.types.StrictBool

• script: pydantic.types.StrictStr

• selected_model_type: edgeimpulse_api.models.keras_model_type_enum.KerasModelTypeEnum

• shape: pydantic.types.StrictStr

• show_advanced_training_settings: pydantic.types.StrictBool

• show_augmentation_training_settings: pydantic.types.StrictBool

• skip_embeddings_and_memory: pydantic.types.StrictBool

• train_test_split: Optional[float]

• trained: pydantic.types.StrictBool

• training_cycles: pydantic.types.StrictInt

• transfer_learning_models: List[edgeimpulse_api.models.transfer_learning_model.TransferLearningModel]

• type: Optional[edgeimpulse_api.models.learn_block_type.LearnBlockType]

• use_learned_optimizer: Optional[pydantic.types.StrictBool]

• visual_layers: List[edgeimpulse_api.models.keras_visual_layer.KerasVisualLayer]

Static methods

from_dict

edgeimpulse_api.models.keras_config.from_dict(
		obj: dict
) ‑> edgeimpulse_api.models.keras_config.KerasConfig

Create an instance of KerasConfig from a dict

Parameters

• obj: dict

Return

edgeimpulse_api.models.keras_config.KerasConfig

from_json

edgeimpulse_api.models.keras_config.from_json(
		json_str: str
) ‑> edgeimpulse_api.models.keras_config.KerasConfig

Create an instance of KerasConfig from a JSON string

Parameters

• json_str: str

Return

edgeimpulse_api.models.keras_config.KerasConfig

mode_validate_enum

edgeimpulse_api.models.keras_config.mode_validate_enum(
		v
)

Parameters

• v

Methods

to_dict

edgeimpulse_api.models.keras_config.to_dict(
		self
)

Returns the dictionary representation of the model using alias

Parameters

• self

to_json

edgeimpulse_api.models.keras_config.to_json(
		self,
		indent=None
) ‑> str

Returns the JSON representation of the model using alias

Parameters

• self

• indent=None

Return

str

to_str

edgeimpulse_api.models.keras_config.to_str(
		self
) ‑> str

Returns the string representation of the model using alias

Parameters

• self

Return

str