Hi @Aigerim,
The following code from the CVNeuralNetLayers docs should help you.
shapes = CVNeuralNetLayers.shape(n_layers=2, n_wires=2)
weights = [np.random.random(shape) for shape in shapes]
def circuit():
CVNeuralNetLayers(*weights, wires=[0, 1])
return qml.expval(qml.X(0))
Please let me know if this solves your problem!