论文复现--关于多视角动作捕捉工具箱 --XRMoCap的研究

分类：动作捕捉
github地址：https://github.com/openxrlab/xrmocap
所需环境：
Ubuntu18.04，conda22.9.0，CUDA11.4

环境配置

conda create -n XRmocap python=3.7 -y
conda activate XRmocap# install ffmpeg for video and images
conda install -y ffmpeg# install pytorch
conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch -y# install pytorch3d
conda install -y -c fvcore -c iopath -c conda-forge fvcore iopath
conda install -y -c bottler nvidiacub
conda install -y pytorch3d -c pytorch3d# install mmcv-full
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.12.1/index.html# install minimal_pytorch_rasterizer
pip install git+https://github.com/rmbashirov/minimal_pytorch_rasterizer.git# install xrprimer
pip install xrprimer# install mmhuman3d
pip install git+https://github.com/open-mmlab/mmhuman3d.git###￥￥￥￥##￥#￥#￥#￥#￥#￥#￥
# install cudnn for mmdeploy
apt-get update && apt-get install -y --no-install-recommends \libcudnn8=8.2.4.15-1+cuda11.4 \libcudnn8-dev=8.2.4.15-1+cuda11.4 \&& apt-mark hold libcudnn8 && \rm -rf /var/lib/apt/lists/*
# install TensorRT for mmdeploy, please get TensorRT from nvidia official website
cd /opt && \tar -xzvf TensorRT-8.2.3.0.Linux.x86_64-gnu.cuda-11.4.cudnn8.2.tar.gz && \rm TensorRT-8.2.3.0.Linux.x86_64-gnu.cuda-11.4.cudnn8.2.tar.gz && \cd TensorRT-8.2.3.0/python && \pip install tensorrt-8.2.3.0-cp38-none-linux_x86_64.whl && \
# install mmdeploy and build ops
cd /opt && \conda install cmake && \git clone https://github.com/open-mmlab/mmdeploy.git && \cd mmdeploy && \git reset --hard 1b048d88ca11782de1e9ebf6f9583259167a1d5b && \pip install -e . && \mkdir -p build && cd build && \cmake -DCMAKE_CXX_COMPILER=g++ -DMMDEPLOY_TARGET_BACKENDS=trt \-DTENSORRT_DIR=/opt/TensorRT-8.2.3.0 \-DCUDNN_DIR=/usr/lib/x86_64-linux-gnu .. && \make -j$(nproc) && make install && \make clean# clone xrmocap
git clone https://github.com/openxrlab/xrmocap.git
cd xrmocap# install requirements for build
pip install -r requirements/build.txt
# install requirements for runtime
pip install -r requirements/runtime.txt
# install requirements for services
pip install -r requirements/service.txt# install xrmocap
rm -rf .eggs && pip install -e .