Ubuntu20.04中复现FoundationPose

🚀 非常重要的环境配置 🚀

• ubuntu 20.04
• cuda 11.8.0
• cudnn v8.9.7
• python 3.9.19
• torch 2.0.0
• 显卡RTX 4060 ti

详细信息如下所示：

1.安装cuda和cudnn

具体可以参考这篇：ubuntu配置多版本cuda+cudnn环境，及版本切换方法

2.下载相关资源

• 下载仓库

git clone https://github.com/NVlabs/FoundationPose.git

• 下载网络权重，并解压到weights/目录中
• 下载demo数据，并解压到demo_data/目录中
• 【可选】下载大规模的数据集：FoundationPose Dataset
• 【可选】在此处下载我们预处理的参考视图，以便运行model-free的小样本版本。

3.环境配置

首先安装anaconda或者miniconda，具体可以参考这篇：【Linux】Ubuntu20.04版本配置pytorch环境2023.09.05【教程】

1. 手动安装eigen3到系统

cd $HOME && wget -q https://gitlab.com/libeigen/eigen/-/archive/3.4.0/eigen-3.4.0.tar.gz && \
tar -xzf eigen-3.4.0.tar.gz && \
cd eigen-3.4.0 && mkdir build && cd build
cmake .. -Wno-dev -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_FLAGS=-std=c++14 ..
sudo make install
cd $HOME && rm -rf eigen-3.4.0 eigen-3.4.0.tar.gz

2. 创建conda环境并安装依赖

# create conda environment
conda create -n foundationpose python=3.9

# activate conda environment
conda activate foundationpose

# Install Eigen3 3.4.0 under conda environment
conda install conda-forge::eigen=3.4.0
export CMAKE_PREFIX_PATH="$CMAKE_PREFIX_PATH:/eigen/path/under/conda"

# install dependencies
python -m pip install -r requirements.txt

# Install NVDiffRast
python -m pip install --quiet --no-cache-dir git+https://github.com/NVlabs/nvdiffrast.git

# Kaolin (Optional, needed if running model-free setup)
python -m pip install --quiet --no-cache-dir kaolin==0.15.0 -f https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-2.0.0_cu118.html

# PyTorch3D
python -m pip install --quiet --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py39_cu118_pyt200/download.html

# Build extensions
CMAKE_PREFIX_PATH=$CONDA_PREFIX/lib/python3.9/site-packages/pybind11/share/cmake/pybind11 bash build_all_conda.sh

4.运行model-based demo

如果配置过程中都没有问题，那么可以直接运行demo

python rum_demo.py

效果如下所示：

5.运行ycbv demo

首先下载ycbv数据集，链接如下：https://huggingface.co/datasets/bop-benchmark/datasets/tree/main/ycbv，数据集的大小是100GB左右

…待补充…

Reference

[1]FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
[2]FoundationPose复现及Realsense应用
[3]【6D位姿估计】数据集汇总 BOP