# QuantityStudyQNN

**Repository Path**: richybai/quantity-study-qnn

## Basic Information

- **Project Name**: QuantityStudyQNN
- **Description**: The code of the paper Quantity study on a novel quantum neural network with alternately controlled gates for binary image classification, which has been accepted by Quantum Inf Process.
- **Primary Language**: Python
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2023-02-24
- **Last Updated**: 2025-07-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# QuantityStudyQNN

The code of the paper [Quantity study on a novel quantum neural network with alternately controlled gates for binary image classification](https://doi.org/10.1007/s11128-023-03929-y), which has been accepted by **Quantum Inf Process**.

## Data preprocessing
- encoder.py: use QPIE (Amplitude Encoding) to convert images into tensorflow-quantum-circuit.
- convert.sh: conversion script.

## Experiments
- binary_classifierCX.py: CX classification code
- binary_classifierCRy.py: CRy classification code
- traincr.sh: training script for CRy.
- traincx.sh: training script for CX.

## Drawing
- Drawing using qpic layer-CR, layer-CX, encoder4qubits
- Drawing using matplotlib accuracy, expressibility

## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{bai2023quantity,
  title={Quantity study on a novel quantum neural network with alternately controlled gates for binary image classification},
  author={Bai, Qi and Hu, Xianliang},
  journal={Quantum Information Processing},
  volume={22},
  number={5},
  pages={184},
  year={2023},
  publisher={Springer}
}
```