We benchmark several widely-used deep learning frameworks and investigate the field programmable gate array (FPGA) deployment for performing traffic sign classification and detection. We evaluate the training speed and inference accuracy of these frameworks on the graphics processing unit (GPU) by training FPGA-deployment-suitable models with various input sizes on German Traffic Sign Recognition Benchmark (GTSRB), a traffic sign classification dataset. Then, selected trained classification models and various object detection models that we train on GTSRB's detection counterpart (i.e., German Traffic Sign Detection Benchmark) are evaluated with inference speed, accuracy, and FPGA power efficiency by varying different parameters such as floating-point precisions, batch sizes, etc. We discover that Neon and MXNet deliver the best training speed and classification accuracy on the GPU in general for all test cases, while TensorFlow is always among the frameworks with the highest inference accuracies. We observe that with the current OpenVINO release, the performance of lightweight models (e.g., MobileNet-v1-SSD, etc.) usually exceeds the requirement of real-time detection without losing much accuracy, while other models (e.g., VGG-SSD, ResNet-50-SSD) generally fail to do so. We also demonstrate that we can adjust the precision of bitstreams and the batch sizes to balance inference speed and accuracy of the applications deployed on the FPGA. Finally, we show that for all test cases, the FPGA always achieves higher power efficiency than the GPU.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Benchmarking Deep Learning Frameworks and Investigating FPGA Deployment for Traffic Sign Classification and Detection


    Beteiligte:
    Lin, Zhongyi (Autor:in) / Yih, Matthew (Autor:in) / Ota, Jeffrey M. (Autor:in) / Owens, John D. (Autor:in) / Muyan-Ozcelik, Pinar (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.09.2019


    Format / Umfang :

    3964500 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    BENCHMARKING DEEP LEARNING FRAMEWORKS WITH FPGA-SUITABLE MODELS ON A TRAFFIC SIGN DATASET

    Lin, Zhongyi / Ota, Jeffrey M. / Owens, John D. et al. | British Library Conference Proceedings | 2018


    Benchmarking Deep Learning Frameworks with FPGA-suitable Models on a Traffic Sign Dataset

    Lin, Zhongyi / Ota, Jeffrey M. / Owens, John D. et al. | IEEE | 2018


    Traffic Sign Classification using Deep Learning

    Pothineni, Ramya Sree / Inampudi, Srinivas / Gudavalli, Lakshmi Yesaswini et al. | IEEE | 2023


    Real Time Traffic Sign Classification Using Deep Learning

    Gurupriya, M. / Veluru, Abhilash / Venkat, Hruday et al. | Springer Verlag | 2025

    Freier Zugriff