Hybrid quantum transfer learning for crack image classification on NISQ hardware

This source code is meant to support the understanding of our paper Hybrid quantum transfer learning for crack image classification on NISQ hardware. Quantum computers possess the potential to process data using a remarkably reduced number of qubits compared to conventional bits, as per theoretical foundations. However, recent experiments have indicated that the practical feasibility of retrieving an image from its quantum encoded version is currently limited to very small image sizes. Despite this constraint, variational quantum machine learning algorithms can still be employed in the current noisy intermediate scale quantum (NISQ) era. An example is a hybrid quantum machine learning approach for edge detection. In our study, we present an application of quantum transfer learning for detecting cracks in gray value images. We compare the performance and training time of PennyLane’s standard qubits with IBM’s qasm_simulator and real backends, offering insights into their execution efficiency.This work was supported by the project AnQuC-3 of the Competence Center Quantum Computing Rhineland-Palatinate (Germany) and by the German Federal Ministry of Education and Research (BMBF) under grant 05M2020 (DAnoBi). Additionally, this work was funded by the Federal Ministry for Economic Affairs and Climate Action (German: Bundesministerium für Wirtschaft und Klimaschutz) under the project EniQmA with funding number 01MQ22007A.Mainly used python, together with qiskit, pennylane and torch. Specific versions of the packages are written in the jupyter notebook or in the requirements.txt or environment.yml. See there for more informatio