activation: Passes in either the activation function (see the
Activations section) or some Theanos or TensorFlow operation.
If nothing is specified, the data is passed along unaltered after the
convolutional process.
•
use_bias: A Boolean for whether or not to use a bias vector in this
layer.
•
kernel_initializer: An initializer for the weight matrix. For more
information, check out the
Initializers section.
•
bias_initializer: Similar to the kernel_initializer, but for the bias.
•
kernel_regularizer: A regularizer function that’s been applied to the
weight matrix. For more information, check out the
Regularizers
section.
•
bias_regularizer: A regularizer function applied to the bias.
•
Do'stlaringiz bilan baham: |