smash.factory.Net.get_weight

Net.get_weight()

Get the weights of the trainable layers of the neural network Net.

Returns:

valuelist[numpy.ndarray]

A list of numpy arrays containing the weights of the trainable layers.

See also

Net.set_weight

Set the values of the weight in the neural network Net.

Examples

>>> from smash.factory import Net
>>> net = Net()
>>> net.add_dense(2, input_shape=3, activation="tanh")
>>> net
+-------------------------------------------------------+
| Layer Type         Input/Output Shape  Num Parameters |
+-------------------------------------------------------+
| Dense              (3,)/(2,)           8              |
| Activation (TanH)  (2,)/(2,)           0              |
+-------------------------------------------------------+
Total parameters: 8
Trainable parameters: 8

Set random weights

>>> net.set_weight(random_state=0)

Get the weight values

>>> net.get_weight()
[array([[ 0.10694503,  0.47145628,  0.22514328],
        [ 0.09833413, -0.16726395,  0.31963799]])]