Dense

class tf_encrypted.layers.dense.Dense(input_shape: List[int], out_features: int)

Standard dense linear layer including bias.

Parameters:

• in_features (int) – number of input features
• out_features (int) – number of output neurons for the layer

backward(d_y, learning_rate)

The backward pass for training.

forward(x)

Forward pass for inference

get_output_shape()

Returns the layer’s output shape