Journal of Applied Optics, Volume. 41, Issue 2, 337(2020)

Using TensorRT for deep learning and inference applications

Lijun ZHOU1... Yu LIU1, Lu BAI2, Fei LIU1 and Yawei WANG1 |Show fewer author(s)
Author Affiliations
  • 1Xi’an Institute of Applied Optics, Xi’an 710065, China
  • 2Xi’an North Electro-optic Science & Technology CO.LTD., Xi’an 710043, China
  • show less
    Figures & Tables(5)
    TensorRT processing flow
    Program test effect
    Effect of TensorRT reasoning in V100 card+ResNet network
    • Table 1. Main members of Context_t structure

      View table
      View in Article

      Table 1. Main members of Context_t structure

      成员描述
      NvVideoDecoder包含视频解码相关的成员和函数
      NvVideoConverter包含视频格式转换相关的成员和函数
      NvEglRenderer包含EGL显示渲染相关函数
      EGLImageKHREGLImage图像数据指针,用于CUDA处理,这个类型来源于EGL开源库
    • Table 2. Main members of TRT_Context class

      View table
      View in Article

      Table 2. Main members of TRT_Context class

      TRT_Context类成员描述
      TRT_Context::buildTrtContext构建Tensorrt上下文
      TRT_Context::getNumTrtInstances获取TRT_context 实例.
      TRT_Context::doInferenceTensorRT 推理接口
    Tools

    Get Citation

    Copy Citation Text

    Lijun ZHOU, Yu LIU, Lu BAI, Fei LIU, Yawei WANG. Using TensorRT for deep learning and inference applications[J]. Journal of Applied Optics, 2020, 41(2): 337

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: OE INFORMATION ACQUISITION AND PROCESSING

    Received: Jun. 17, 2019

    Accepted: --

    Published Online: Apr. 23, 2020

    The Author Email:

    DOI:10.5768/JAO202041.0202007

    Topics