I am trying to use SGD to train a network that connect two circuits together. In the first circuit, after some operators, I want to trace out a few qubits. Then the density matrix after partial trace is input to the second cricuit. But I get some errors like this. TypeError must be real number, not…

Hi @Jinkai_Tian ! In your cost function, after you calculate hidden_state you should add this line: hidden_state = qml.math.toarray(hidden_state) This will prevent the first layer to be differentiated a second time from within the second layer, but it should solve your problem and still let you tr…

Thanks! Your suggestion solved my problem!

Does gradient information flows from one circuit to its fromer circuit?

PennyLane Help

CatalinaAlbornoz November 8, 2022, 11:40pm 4

Awesome @Jinkai_Tian! I’m glad this helped.

Topic		Replies	Views
How the gradient information flows from a circuit to its original circuit？ PennyLane Help	1	43	July 12, 2024
Vectorization of gradient circuits PennyLane Help	5	400	July 12, 2023
Training parameters in two quantum circuits PennyLane Help	4	875	January 6, 2022
Using PyTorch Gradients PennyLane Help	9	3156	January 5, 2021
Derivative of circuit PennyLane Help	5	711	July 2, 2021

Does gradient information flows from one circuit to its fromer circuit?

Related topics