The diversity of software and hardware forces programmers to spend a great deal of time optimizing their source code,which often requires specific treatment for each *** problem becomes critical on embedded devices,wh...
详细信息
The diversity of software and hardware forces programmers to spend a great deal of time optimizing their source code,which often requires specific treatment for each *** problem becomes critical on embedded devices,where computational and memory resources are strictly *** play an essential role in deploying source code on a target device through the *** this work,a novel backend for the open neural network compiler(ONNC)is proposed,which exploits machine learning to optimize code for the ARM Cortex-M *** backend requires minimal changes to openneuralnetwork Exchange(ONNX)*** novel optimization techniques are also incorporated in the backend,such as quantizing the ONNX model’s weight and automatically tuning the dimensions of operators in *** performance of the proposed framework is evaluated for two applications:handwritten digit recognition on the Modified National Institute of Standards and Technology(MNIST)dataset and model,and image classification on the Canadian Institute For Advanced Research and 10(CIFAR-10)dataset with the AlexNet-Light *** system achieves 98.90%and 90.55%accuracy for handwritten digit recognition and image classification,***,the proposed architecture is significantly more lightweight than other state-of-theart models in terms of both computation time and generated source code *** the system perspective,this work provides a novel approach to deploying direct computations from the available ONNX models to target devices by optimizing compilers while maintaining high efficiency in accuracy performance.
暂无评论