Making quanvolutional neural net weights trainable

PennyLane Help
21

Hi @glassnotes,

I updated the code in the post above post above.

It should work now out of the box. If not, check out my repo at github: https://github.com/dymat/TrainableQuanvolution

Best regards,
~dymat

22

@dymat thank you for posting the code I will try to run it and get back to you asap :slight_smile:

1 Like
23

Thanks @dymat, it’s very cool that you had some positive results training on MNIST (at least for the 1 quantum layer). If you’re interested, I think this would make a great demo! We have just launched a community space for demos. Since you already have a Jupyter Notebook, is should just be a case of creating an issue here (see instructions).

On to your question about the gradient for two layers, I had a quick look and unfortunately nothing jumped out as a problem. I might have a chance to dig a bit deeper next week, however for now I would suggest some debugging. For example, what if we swapped out the quantum circuit (self.circuit) with a simple torch function? If you still aren’t getting a gradient in the first layer, it’s probably an issue with the big for loop in forward(). Otherwise, we can look at if it’s an issue on the PL side.

Hope this helps a bit!
Tom

24

@dymat went through your code and ran it a few times with some changes. I haven’t found the source of the gradient problem yet. But will still keep looking and update if i find something!

25

Hi @Tom_Bromley,

publishing our notebook as a demo sounds cool. I would use the one-layer example. Can we change the demo notebook later on, if we find the source of the gradient problem in two-layer networks?

Best regards,
D

26

Ok, I’ve checked the instructions and see that my question is obsolete, since the code lives in my repo.

1 Like
27

Hi @dymat, awesome, we’re looking forward to seeing your demo! Let us know if you have any further questions while getting it ready.

28

Hi @glassnotes, the demo request is submitted (https://github.com/PennyLaneAI/qml/issues/165).

Best regards,
D

2 Likes
29

Hi @dymat @Tom_Bromley , has this issue of quantum layer 0 not getting any gradients been solved? Any update?

30

Hi @gojiita_ku, thank you for your question and sorry for the delay in responding!
I haven’t seen gradient issues recently. Are you experiencing a similar issue?

If so, please share with us a minimal version of your code, the output of qml.about(), and your full error traceback.

If you run our quanvolutional neural networks demo as-is, does it work properly?

I’ll be looking out for your answer!

1 Like
32

Hi @Tom_Bromley and @CatalinaAlbornoz,

Could you please give a code example in this case about how to swap out the quantum circuit (self.circuit ) with a simple torch function as suggested by Tom?

For example, what if we swapped out the quantum circuit (self.circuit ) with a simple torch function ?

Many thanks!

33

Hi @CatalinaAlbornoz. I run this notebook and found parameters in both of two QonvLayers were updated successfully every epoch. But if I change the code a little bit (e.g. build the model using nn.Module instead of nn.Sequential), I found parameters in the first QonvLayer were not updated. I don’t know the reason. I’ve uploaded my notebook file. Could you please take a look if you have free time? Many thanks!

StackedQuanvolutions.py (5.3 KB)

Here is the output of qml.about():

Name: PennyLane
Version: 0.28.0
Summary: PennyLane is a Python quantum machine learning library by Xanadu Inc.
Home-page: https://github.com/XanaduAI/pennylane
Author: 
Author-email: 
License: Apache License 2.0
Location: /Users/chenyixiong/opt/anaconda3/lib/python3.9/site-packages
Requires: appdirs, autograd, autoray, cachetools, networkx, numpy, pennylane-lightning, requests, retworkx, scipy, semantic-version, toml
Required-by: PennyLane-Lightning, PennyLane-qiskit, pennylane-qulacs
Platform info:           macOS-10.16-x86_64-i386-64bit
Python version:          3.9.13
Numpy version:           1.21.5
Scipy version:           1.9.1
Installed devices:
- lightning.qubit (PennyLane-Lightning-0.28.2)
- qiskit.aer (PennyLane-qiskit-0.28.0)
- qiskit.basicaer (PennyLane-qiskit-0.28.0)
- qiskit.ibmq (PennyLane-qiskit-0.28.0)
- qiskit.ibmq.circuit_runner (PennyLane-qiskit-0.28.0)
- qiskit.ibmq.sampler (PennyLane-qiskit-0.28.0)
- qulacs.simulator (pennylane-qulacs-0.28.0)
- default.gaussian (PennyLane-0.28.0)
- default.mixed (PennyLane-0.28.0)
- default.qubit (PennyLane-0.28.0)
- default.qubit.autograd (PennyLane-0.28.0)
- default.qubit.jax (PennyLane-0.28.0)
- default.qubit.tf (PennyLane-0.28.0)
- default.qubit.torch (PennyLane-0.28.0)
- default.qutrit (PennyLane-0.28.0)
- null.qubit (PennyLane-0.28.0)
34

Hi @gojiita_ku,

I’m really sorry I somehow didn’t see your question when you asked it. Are you still having the same problem? Do you still need our help?