TensorRT 下载地址、开发文档地址、Python 实例地址以及接口地址

1.TensorRT 下载地址:

https://developer.nvidia.com/nvidia-tensorrt-download

2.TensorRT 开发者文档:

https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html

3.TensorRT C++实例

https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#samples

4.TensorRT Python 实例:

https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#python_topics

5.TensorRT C++ 接口介绍:

https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#network_c

6.TensorRT Python 接口介绍:

https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/python_api/index.html

7.TensorRT 开源项目:

--TensorRT&Deepstream:

● https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps

--TensorRT & Tegra 平台:

● https://github.com/dusty-nv/jetson-inference

8.怎么查看当前系统中 TensorRT 版本:

dpkg -l | grep nvinfer

9.常用 TensorFlow/TensorRT 模型:

https://github.com/NVIDIA-AI-IOT/tf_trt_models

10.将 TensorFlow 中的.pb 模型转化成.uff 格式:

convert-to-uff frozen_inference_graph.pb -p config.py -t

11.TensorRT 在 Python 中添加自定义层 Plugin 的示例:

https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#add_custom_layer_python

12.TensorRT 集成 TensorFlow 环境配置:

https://developer .nvidia-china.com/forum.php?mod=viewthread&tid=8788&extra=page%3D1

问题来源

NVIDIA AI 计算专区