Add demo on loading classical data with low-depth circuits #1554
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…nist/requirements.in and update the reference types in demonstrations_v2/low_depth_circuits_mnist/metadata.json
Your preview is ready 🎉!You can view your changes here
|
DSGuala
reviewed
Sep 29, 2025
Contributor
DSGuala
left a comment
DSGuala
left a comment
There was a problem hiding this comment.
Made an initial skim and left comments. Overall a very nice/complete first draft.
Still pending from my side:
- In depth review of the text for clarity
- In depth review of the code for efficiency and output
But basically I think 1 or two more rounds of review and this should be ready to go.
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
Co-authored-by: Diego <[email protected]>
…details one the three steps
DSGuala
reviewed
Oct 16, 2025
Co-authored-by: Daniela Angulo <[email protected]>
Co-authored-by: Daniela Angulo <[email protected]>
Co-authored-by: Diego <[email protected]>
DSGuala
reviewed
Nov 20, 2025
DSGuala
reviewed
Nov 20, 2025
…humbnails Add images and update metadata
Co-authored-by: Daniela Angulo <[email protected]>
Co-authored-by: Daniela Angulo <[email protected]>
DSGuala
approved these changes
Nov 24, 2025
Contributor
DSGuala
left a comment
DSGuala
left a comment
There was a problem hiding this comment.
Looks great, left some final comments/suggestions, but ready to go from my side once they're addressed.
| n = 2 * int(np.log2(N)) | ||
| # reorder pixels hierarchically | ||
| states = np.reshape(images, (batchsize, *(2,) * n)) | ||
| states = np.transpose(states, [0] + [ax + 1 for q in range(n // 2) for ax in (q, q + n // 2)]) |
Contributor
There was a problem hiding this comment.
This should remove the horizontal scroll bar from the code block
Suggested change
| states = np.transpose(states, [0] + [ax + 1 for q in range(n // 2) for ax in (q, q + n // 2)]) | |
| states = np.transpose(states, | |
| [0] + [ax + 1 for q in range(n // 2) for ax in (q, q + n // 2)]) |
| import jax | ||
| import pennylane as qml | ||
|
|
||
| # JAX supports the single-precision numbers by default. The following line enables double-precision. |
Contributor
There was a problem hiding this comment.
This should remove the horizontal scroll bar.
Suggested change
| # JAX supports the single-precision numbers by default. The following line enables double-precision. | |
| # JAX supports the single-precision numbers by default. | |
| # The following line enables double-precision. |
Comment on lines
+168
to
+169
| :param circuit_layout: List of tuples containing gate types ('RY' or 'CNOT') and their target wires. | ||
| :return circuit: A JAX-compiled quantum circuit function that takes parameters and returns the quantum state. |
Contributor
There was a problem hiding this comment.
This should remove the horizontal scroll bar
Suggested change
| :param circuit_layout: List of tuples containing gate types ('RY' or 'CNOT') and their target wires. | |
| :return circuit: A JAX-compiled quantum circuit function that takes parameters and returns the quantum state. | |
| :param circuit_layout: List of tuples containing gate types ('RY' or 'CNOT') | |
| and their target wires. | |
| :return circuit: A JAX-compiled quantum circuit function that takes parameters and | |
| returns the quantum state. |
| rec_0 = FRQI_decoding(states_01[labels_01 == 0][idx_0][None, :])[0] | ||
| rec_1 = FRQI_decoding(states_01[labels_01 == 1][idx_1][None, :])[0] | ||
|
|
||
| # Create a grid of figures to show both the fidelity distribution and the original and reconstructed images |
Contributor
There was a problem hiding this comment.
This should remove the horizontal scroll bar
Suggested change
| # Create a grid of figures to show both the fidelity distribution and the original and reconstructed images | |
| # Create a grid of figures to show both the fidelity distribution and the original | |
| # and reconstructed images |
Comment on lines
+397
to
+398
| ) # we select the real part only, as the the imaginary part is zero since we only use RY and CNOT gates | ||
| y_all = jnp.asarray(labels_01, dtype=jnp.int32) |
Contributor
There was a problem hiding this comment.
This should remove the horizontal scroll bar.
Suggested change
| ) # we select the real part only, as the the imaginary part is zero since we only use RY and CNOT gates | |
| y_all = jnp.asarray(labels_01, dtype=jnp.int32) | |
| ) # we select the real part only | |
| # the imaginary part is zero since we only use RY and CNOT gates | |
| y_all = jnp.asarray(labels_01, dtype=jnp.int32) |
Comment on lines
+366
to
+367
| (loss, acc), grads = jax.value_and_grad(lambda p: loss_acc(p, batch_x, batch_y), has_aux=True)( | ||
| params |
Contributor
There was a problem hiding this comment.
This should remove the horizontal scroll bar
Suggested change
| (loss, acc), grads = jax.value_and_grad(lambda p: loss_acc(p, batch_x, batch_y), has_aux=True)( | |
| params | |
| func = lambda p: loss_acc(p, batch_x, batch_y) | |
| (loss, acc), grads = jax.value_and_grad(func, has_aux=True)( | |
| params |
| quantum circuits to load classical image data into quantum states. | ||
|
|
||
| This demo gives an introduction to the paper **“Typical Machine Learning Datasets as | ||
| Low‑Depth Quantum Circuits”** (2025). We will discuss the following three steps: |
Contributor
There was a problem hiding this comment.
Something about "discuss steps" with "define, construct, train and evaluate" sounds a bit strange to me.
Suggested change
| Low‑Depth Quantum Circuits”** (2025). We will discuss the following three steps: | |
| Low‑Depth Quantum Circuits”** (2025). We will do the following: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Title:
Add demo on loading classical data with low-depth circuits
Summary:
This pull request adds a new demonstration on how to efficiently load classical image data into quantum states using low-depth quantum circuits, based on the paper "Typical Machine Learning Datasets as Low‑Depth Quantum Circuits". The demo uses the MNIST dataset and shows how to train a variational quantum classifier on the encoded data. This demo leverages the new qml.data module for dataset loading.
Relevant references:
Possible Drawbacks:
The dataset required for this demo is large (~1GB), which might be a consideration for users with limited bandwidth or storage.
Related GitHub Issues:
None
If you are writing a demonstration, please answer these questions to facilitate the marketing process.
Promote the new
qml.datafeature for loading datasets and show a PennyLane implementation of a recent paper on efficient data loading for QML.QML researchers, students, and practitioners interested in efficient data loading techniques and their application to image classification tasks.
Quantum Machine Learning, Quantum Datasets, Image Loading, Low-depth circuits, Variational Quantum Classifier, MNIST, PennyLane, qml.data
(more details here)