TensorRT

TensorRT zoo C++ API: https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/c_api/_nv_infer_plugin_8h.html

1. SSD-VGG16

• TensorRT 3.0 : https://github.com/chenzhi1992/TensorRT-SSD

2. SSD-MobileNet

• TensorRT 4.0(class 4) : https://github.com/Ghustwb/MobileNet-SSD-TensorRT

3. SSDLite-MobileNet V2

• TF to Caffe : https://github.com/chuanqi305/MobileNetv2-SSDLite

4. YOLOv2

5. YOLOv3

6. TinyYOLO

7. Pelee : https://github.com/ginn24/Pelee-TensorRT

8. Openpose

• Openpose plus : https://github.com/tensorlayer/openpose-plus
• Openpose-trt-opt : https://github.com/haanjack/openpose-trt-optimize
• slide: https://www.slideshare.net/deview/232-dl-inference-optimization-using-tensor-rt-1-119162975

NVIDIA PROFILER

• slide: https://imsc.uni-graz.at/haasegu/Lectures/HPC-II/SS15/Siegmann/nvvp_memcheck.pdf
• nvidia slide: https://www.olcf.ornl.gov/wp-content/uploads/2018/02/SummitDev_NVIDIA-Profilers.pdf
• tuitorial: https://docs.nvidia.com/cuda/profiler-users-guide/index.html#nvprof-command-line-options-print
• nvidia blog: https://devblogs.nvidia.com/cuda-pro-tip-nvprof-your-handy-universal-gpu-profiler/

Inference

• Best Practice: https://docs.nvidia.com/deeplearning/sdk/tensorrt-best-practices/index.html
• Code: https://github.com/NVIDIA/tensorrt-laboratory/tree/master/examples/00_TensorRT
• Inference Time: https://arleyzhang.github.io/articles/fda11be6/