This repo provides C++ implementation for human pose detection system based on TensorRT framework that runs on Windows Machine. It is based on pose detection program developed by NVIDIA. Pose detection model runs at up to about 500 FPS on RTX-3070 GPU with 224x224 ResNet input size.
The following environment was set for the experiment but if you have a different Graphic Card, you need to download and install TensorRT / CUDA that matches your GPU version.
- Windows 10
- Visual Studio 2017
- RTX 3070 GPU
- TensorRT 7.2.1.6
- CUDA 11.1, Cudnn 8
- Python 3.7
- Torch 1.8.1
- Install PyTorch
pip3 install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio===0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
- Download and install CUDA and CUDNN by following this installation guide.
- Download the TensorRT zip file that matches your Windows version.
- Install TensorRT by copying the DLL files from <tensorrt_path>/lib to your CUDA installation directory. For more information, refer to TensorRT installation guideline.
move <TensorRT_Installpath>/lib/*.dll "C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v11.1/bin"
- Install trt_pose for parsing the trained pytorch model to an onnx graph model. For more information, refer to trt_pose installation guide.
git clone https://github.com/NVIDIA-AI-IOT/trt_pose
cd trt_pose
python setup.py install
- Clone this github repository
cd ..
git clone https://github.com/batselem/Human_pose_detection
cd Human_pose_detection
- Download a pretrained resnet model, resnet18_baseline_att_224x224_A and put it in the current project folder.
- Create an onnx model, optimize the model using TensorRT and build a runtime inference engine.
python convert2onnx.py -i resnet18_baseline_att_224x224_A_epoch_249.pth -o trt_pose.onnx
<tensorrt_path>/bin/trtexec.exe -- --explicitBatch --saveEngine=trt_pose_fp16.engine --fp16
- Open the solution with Visual Studio. Select
x64andReleasefor the configuration and start building the project.
- https://github.com/NVIDIA-AI-IOT/trt_pose - Real-time pose estimation (Python and C++)
- https://github.com/CaoWGG/TensorRT-YOLOv4 - Object detection based on Tensorrt (C++)