peal.architectures.interfaces.FCConfig

class peal.architectures.interfaces.FCConfig

Bases: BaseModel

The config template for a Fully Connected Layer.

Methods

Attributes

config_name	The type of config.
dropout	Whether to use batchnorm or not.
num_neurons	The number of neurons in the layer.
tensor_dim	The dimension of the tensor.

config_name: str = 'FCConfig'

The type of config. This is necessary to find config class from yaml config

num_neurons: pydantic.PositiveInt = 512

The number of neurons in the layer.

dropout: float = 0.0

Whether to use batchnorm or not.

tensor_dim: int = 0

The dimension of the tensor. Options: [0, 1, 2, 3]