smash.factory.Net.set_weight

Net.set_weight(value=None, random_state=None)

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

Parameters:

valuelist[float or numpy.ndarray] or None, default None

The list of values to set to the weights of all layers. If an element of the list is a numpy.ndarray, its shape must be broadcastable into the weight shape of that layer. If not used, initialization methods defined in trainable layers will be used with a random or specified seed depending on random_state.

random_stateint or None, default None

Random seed used for the initialization method defined in each trainable layer. Only used if value is not set.

Note

If not given, the parameters will be initialized with a random seed.

See also

Net.get_weight

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

Examples

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

Set weights with specified values

>>> import numpy as np
>>> net.set_weight([np.array([[1, 2, 3], [4, 5, 6]])])

Get the weight values

>>> net.get_weight()
[array([[1, 2, 3],
        [4, 5, 6]])]

Set random weights

>>> net.set_weight(random_state=0)
>>> net.get_weight()
[array([[ 0.05636498,  0.24847928,  0.11866093],
        [ 0.05182664, -0.08815584,  0.16846401]])]