# Proper gradient and differentiation method for default.tensor with tensorflow **URL:** \ **Category:** PennyLane Help\ **Created:** [March 20, 2025, 12:44pm UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259 "2025-03-20T12:44:27Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Lucas](https://avatars.discourse-cdn.com/v4/letter/l/ba8739/32.png) [@Lucas](https://discuss.pennylane.ai/u/Lucas)\ **Post date:** [March 20, 2025, 12:44pm UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259/1 "2025-03-20T12:44:27Z")
I have a GAN with a quantum generator using pennylane for the generator. I use tensorflow (`tf.GradientTape`) to train the model. I want to use `default.tensor` so I can make use of mps. The problem is that when running the circuit on `default.tensor` the function `tape.gradient` takes incredibly long while using `default.qubit` does not take as long. I was wondering what the optimal parameters are for the `default.tensor` device as I don’t think backpropagation works for instance. I am now using: `"default.tensor",, method="mps"` and `interface='tf', diff_method="parameter-shift"`. Also the `qml.qnn.KerasLayer` does not seem to work with `default.tensor` and thus I have the QNode wrapped in custom layer i.e. `class QuantumLayer(tf.keras.layers.Layer):` etc. Thank you in advance for the help. Output from `qml.about()`: ```auto Name: PennyLane Version: 0.39.0 Summary: PennyLane is a cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. Train a quantum computer the same way as a neural network. Home-page: https://github.com/PennyLaneAI/pennylane Author: Author-email: License: Apache License 2.0 Location: /Users/lucas/MPS_Quantum_Finance/.venv/lib/python3.10/site-packages Requires: appdirs, autograd, autoray, cachetools, networkx, numpy, packaging, pennylane-lightning, requests, rustworkx, scipy, toml, typing-extensions Required-by: PennyLane-Cirq, PennyLane_Lightning Platform info: macOS-10.16-x86_64-i386-64bit Python version: 3.10.15 Numpy version: 1.26.4 Scipy version: 1.14.1 Installed devices: - default.clifford (PennyLane-0.39.0) - default.gaussian (PennyLane-0.39.0) - default.mixed (PennyLane-0.39.0) - default.qubit (PennyLane-0.39.0) - default.qutrit (PennyLane-0.39.0) - default.qutrit.mixed (PennyLane-0.39.0) - default.tensor (PennyLane-0.39.0) - null.qubit (PennyLane-0.39.0) - reference.qubit (PennyLane-0.39.0) - cirq.mixedsimulator (PennyLane-Cirq-0.39.0) - cirq.pasqal (PennyLane-Cirq-0.39.0) - cirq.qsim (PennyLane-Cirq-0.39.0) - cirq.qsimh (PennyLane-Cirq-0.39.0) - cirq.simulator (PennyLane-Cirq-0.39.0) - lightning.qubit (PennyLane_Lightning-0.39.0) None ``` ---
**Author:** ![CatalinaAlbornoz](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/catalinaalbornoz/32/1196_2.png) [@CatalinaAlbornoz](https://discuss.pennylane.ai/u/CatalinaAlbornoz)\ **Post date:** [March 20, 2025, 9:46pm UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259/2 "2025-03-20T21:46:42Z")
Hi @Lucas , I noticed a couple of things that can help: - `default.tensor` does not currently support differentiation. If you need differentiation then `default.qubit` might be best. If you want to find other ways of using `default.tensor` you can check out our [demos that use `default.tensor`](https://pennylane.ai/search?q=default.tensor&contentType=DEMO) or the [documentation for `default.tensor`](https://docs.pennylane.ai/en/stable/code/api/pennylane.devices.default_tensor.DefaultTensor.html). - `diff_method="parameter-shift"` is the slowest method. Should you choose to change the device, it’s generally best not to set the `diff_method`. If you don’t set it then PennyLane will automatically choose the best diff\_method for the device you’re using. - `qnn.KerasLayer` will be deprecated soon. I would recommend using PyTorch instead if possible. The [demo on TorchLayers](https://pennylane.ai/qml/demos/tutorial_qnn_module_torch) can be helpful here. - If possible, upgrade your version of PennyLane. While this is probably not the cause for the issues you’re seeing, it’s always best to use the latest PennyLane version. At the moment the latest stable version is v0.40. You can always check what’s the latest version at the top of the [pennylane.ai](https://pennylane.ai/) homepage. You can upgrade the version with `pip install pennylane --upgrade`. I hope this helps! ---
**Author:** ![Lucas](https://avatars.discourse-cdn.com/v4/letter/l/ba8739/32.png) [@Lucas](https://discuss.pennylane.ai/u/Lucas)\ **Post date:** [March 24, 2025, 10:30am UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259/3 "2025-03-24T10:30:09Z")
Thank you for your reply. As my research is based on mps is there another way of using mps with differentiation on pennylane? ---
**Author:** ![Lucas](https://avatars.discourse-cdn.com/v4/letter/l/ba8739/32.png) [@Lucas](https://discuss.pennylane.ai/u/Lucas)\ **Post date:** [March 24, 2025, 2:19pm UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259/4 "2025-03-24T14:19:23Z")
Also on the Pennylane website it says that default.tensor does support differentiation when using the parameter shift rule: [https://pennylane.ai/devices/default-tensor](https://pennylane.ai/devices/default-tensor) So is it that parameter-shift rule just much slower and that’s why the code the code is slow? Thank you again for your help ---
**Author:** ![CatalinaAlbornoz](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/catalinaalbornoz/32/1196_2.png) [@CatalinaAlbornoz](https://discuss.pennylane.ai/u/CatalinaAlbornoz)\ **Post date:** [March 24, 2025, 7:48pm UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259/5 "2025-03-24T19:48:50Z")
Hi @Lucas , You’re totally right. `default.tensor` doesn’t natively support differentiation with `backprop` and `adjoint`, which are more performant. But PennyLane _does_ support other methods such as `parameter-shift` on all devices including `default.tensor`. One way you can test the cause for the slowdown is to set `diff_method="parameter-shift"` when using `default.qubit`. If you get a big slowdown then this will be an indication that the diff\_method might be the main cause. Please let us know what you find with this test! You can try using tools like `timeit` to find execution times or a profiler such as `snakeviz` to get a deeper look into the slower processes. Let me know if you need an example on how to use `timeit`. I hope this helps! ---
**Author:** ![Lucas](https://avatars.discourse-cdn.com/v4/letter/l/ba8739/32.png) [@Lucas](https://discuss.pennylane.ai/u/Lucas)\ **Post date:** [March 25, 2025, 2:28pm UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259/6 "2025-03-25T14:28:01Z")
Hi Catalina, Thank you for the tip. I checked and: When using `default.qubit` the code is fine with `parameter-shift` (though it is obviously slower then using `best`). It is just when changing to `default.tensor` that it slows down massively. So it would seem the issue is with changing the device on the `Qnode`. However, the slow down occurs when I am training the generator(or discriminator) in my GAN where I call the `Qnode` for creating a fake sample for the discriminator. The `tf.GradientTape` method has to propagate through the generator, even though the generator’s weights aren’t being updated or any gradients calculated, which only happens later. So what I am thinking is that if the generator’s computational graph is complex or inefficient (maybe because mps involves more steps), this is the bottleneck. Not necessarily computing the gradients but just tracking the operations in the quantum circuit itself. I hope this makes sense and I was clear enough with my explanation. Thank you. ---
**Author:** ![CatalinaAlbornoz](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/catalinaalbornoz/32/1196_2.png) [@CatalinaAlbornoz](https://discuss.pennylane.ai/u/CatalinaAlbornoz)\ **Post date:** [March 25, 2025, 6:03pm UTC](https://discuss.pennylane.ai/t/proper-gradient-and-differentiation-method-for-default-tensor-with-tensorflow/8259/7 "2025-03-25T18:03:34Z")
Thanks for sharing these insights @Lucas ! They’re very useful. Are you able to share some code that we could use to investigate the issue further? For example, if you based you code on the [PennyLane demo on Quantum GANs](https://pennylane.ai/qml/demos/tutorial_quantum_gans), what parts of the code did you change? If you can share an example that we can reproduce then we may be able to identify the cause of the slowdown.