ertk.tensorflow.models.TFModelConfig

class ertk.tensorflow.models.TFModelConfig(optimiser: str = 'adam', opt_params: ~typing.Dict[str, ~typing.Any] = <factory>, learning_rate: float = 0.001, n_features: int = -1, n_classes: int = -1, loss: str = 'sparse_categorical_crossentropy')

Bases: ERTKConfig

Configuration for a TensorFlow model.

__init__(optimiser: str = 'adam', opt_params: ~typing.Dict[str, ~typing.Any] = <factory>, learning_rate: float = 0.001, n_features: int = -1, n_classes: int = -1, loss: str = 'sparse_categorical_crossentropy') → None

Methods

__init__([optimiser, opt_params, ...])

Inherited Methods

from_config(config)	Create config object from any compatible config.
from_file(path[, override])	Create config from YAML file and optionlly override some values.
merge_with_args([args])	Merge config with command-line arguments.
to_dictconfig()	Convert config to DictConfig.
to_file(path)	Write config to YAML file.
to_string()	Generate YAML string representation of config.

Attributes

learning_rate	The learning rate to use.
loss	The loss function to use.
n_classes	The number of classes in the output data.
n_features	The number of features in the input data.
optimiser	The optimiser to use.
opt_params	The parameters to pass to the optimiser.

learning_rate: float = 0.001

The learning rate to use.

loss: str = 'sparse_categorical_crossentropy'

The loss function to use.

n_classes: int = -1

The number of classes in the output data.

n_features: int = -1

The number of features in the input data.

opt_params: Dict[str, Any]

The parameters to pass to the optimiser.

optimiser: str = 'adam'

The optimiser to use.