Installation guide安装引导

Install WAPR 0.0.5安装 WAPR 0.0.5

Reuse a compatible Linux or Windows NVIDIA GPU environment with CUDA-enabled PyTorch. The wheel does not bundle PyTorch, model weights or datasets. OGL requires a compatible CUDA toolkit, C++ compiler and CMake. Linux also needs OpenGL/EGL development libraries; Windows needs MSVC C++ build tools.

复用兼容的 Linux 或 Windows NVIDIA GPU 环境及支持 CUDA 的 PyTorch。wheel 不打包 PyTorch、模型权重或数据集。OGL 需要兼容的 CUDA toolkit、C++ 编译器和 CMake；Linux 还需 OpenGL/EGL 开发库，Windows 需要 MSVC C++ 构建工具。

python -m pip install -U wapr==0.0.5
python -m wapr.bootstrap
python -c "from wapr.bootstrap import export_examples; export_examples('wapr_examples')"
python wapr_examples/02_one_category_one_instance.py

The universal wheel declares Python ≥3.8. This is a package requirement, not a guarantee that every optional dependency supports every Python, CUDA or operating-system version. Windows without TensorRT uses PyTorch by default; the TensorRT backend requires TensorRT 10. The supplied SAM3D and robot planning setups require Linux. macOS pose inference is not supported.

通用 wheel 声明 Python ≥3.8；这不表示所有可选依赖支持每种 Python、CUDA 或操作系统版本。Windows 未安装 TensorRT 时默认使用 PyTorch；TensorRT 后端需要 TensorRT 10。随包 SAM3D 与机器人规划方案需要 Linux。不支持 macOS 位姿推理。

Core preparation reuses the existing PyTorch environment and asks before replacing installed dependencies. Optional features are prepared on first use, including detection dependencies in examples 01, 08, 09 and 12. Importing an example alone does not install optional features; Ultralytics is not a core dependency. For manual preparation, follow optional feature setup. The first example obtains its required resources and may take longer on its first run.

核心准备复用已有 PyTorch 环境，更换已有依赖前需确认。可选功能在首次使用时准备，示例 01、08、09、12 会先准备检测依赖；仅导入示例不会安装可选功能，Ultralytics 不属于基础依赖。手动准备方式见扩展环境。首个示例会获取所需资源，首次运行可能耗时较长。

Source usage源码使用

For editable recipes, clone the repository and use a compatible existing environment. The source installer described in source setup is a separate route; its repository-relative paths do not describe the installed wheel. Conda is optional.

需要修改仓库示例时可克隆源码，并使用兼容的已有环境。源码安装说明是独立路线，其中仓库相对路径不代表 wheel 的缓存位置；不要求使用 Conda。

git clone https://github.com/WangYuLin-SEU/WAPR.git