Hi, I am trying this tutorial for CV-QNN: https://strawberryfields.ai/photonics/demos/run_quantum_neural_network.html.
However, when I change the number of modes to 2 modes, the output cost and fidelity become nan.
Hi, I am trying this tutorial for CV-QNN: https://strawberryfields.ai/photonics/demos/run_quantum_neural_network.html.
However, when I change the number of modes to 2 modes, the output cost and fidelity become nan.
Hi @namnguyen0510! This was a bug that was recently fixed by the team on the GitHub repo: Fixes the QNN example to use a safe absolute value function for multiple modes by antalszava · Pull Request #589 · XanaduAI/strawberryfields · GitHub
But good catch, it looks like the website still needs to be updated! In the meantime, you can try using the updated example file, strawberryfields/quantum_neural_network.py at master · XanaduAI/strawberryfields · GitHub directly from the GitHub repo
Let me know if you have any other questions!
Hi, I tried the code but there is another bug:
TypeError: Engine() missing 1 required positional argument: ‘num_subsystems’
Which version of Strawberry Fields did the error arise with? The SF version can be checked for example by looking at the output of sf.about()
, after the import strawberryfields as sf
import statement.