I am currently working on a project wherein I have to implement a Quantum Convolutional Neural Network. The best options for NISQ devices are hybrid algorithms, so I will try integrating quantum layers into existing CNN architectures. The primary idea is to utilize either Quantum Filters as they do in Quanvolutional NNs or to utilize PQCs as Convolutional Layers.

Please provide a comparative analysis of these packages based on your experience. The primary factors to consider include integrability with Classical Models, availability of QML tools such as optimizers and different encoding schemes, and availability of simulators and circuit visualizers. Which package would serve best for this project?

I am currently quite familiar with TensorFlow and Qiskit but do not mind learning other languages. Additionally, I have written code for QML models however I have done that from scratch and not used existing packages.

Thanks! Any help is greatly appreciated.

  • $\begingroup$ which part of the CNN (the convolution or the backpropagation) do you intend to substitute quantum algorithms for? $\endgroup$
    – James
    Commented Jun 29, 2023 at 8:47
  • 2
    $\begingroup$ As currently phrased, I'm afraid this question will be closed as it's quite opinion-based. I suggest asking instead for the different functionalities handled by each framework $\endgroup$
    – Tristan Nemoz
    Commented Jun 29, 2023 at 9:36

1 Answer 1


I have some experience in pennylane, which is designed primarily for QML. You can easily define a qnode and integrate it into backend ML frameworis like pytorch or tensorflow. See examples


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.