|
Download README.md from Charlie839242/StreamTAP3D: direct link, hf CLI and curl.
- Browser
- Download file 1.05 kB
-
https://huggingface.co/Charlie839242/StreamTAP3D/resolve/main/README.md
- Command line
-
hf download hf://Charlie839242/StreamTAP3D/README.md
-
curl -L -H "Authorization: Bearer $HF_TOKEN" -o README.md https://huggingface.co/Charlie839242/StreamTAP3D/resolve/main/README.md
1.05 kB
| # 环境安装 | |
| conda 环境名为 `streamtap3d`。 | |
| **1. 创建 conda 环境** | |
| ```bash | |
| conda create -n streamtap3d python=3.10 -y | |
| conda activate streamtap3d | |
| ``` | |
| **2. 安装 PyTorch(CUDA 12.8)** | |
| ```bash | |
| pip install torch==2.8.0 torchvision==0.23.0 --index-url https://download.pytorch.org/whl/cu128 | |
| ``` | |
| > PyTorch 2.8.0(CUDA 12.8)是推荐版本。其他 CUDA 版本见 [PyTorch Get Started](https://pytorch.org/get-started/locally/)。 | |
| **3. 安装 Python 依赖** | |
| ```bash | |
| pip install Pillow huggingface_hub einops safetensors opencv-python tqdm scipy \ | |
| hydra-core omegaconf av imageio imageio-ffmpeg matplotlib python-box rich numpy | |
| ``` | |
| **4. 安装 FlashInfer** | |
| ```bash | |
| pip install --index-url https://pypi.org/simple flashinfer-python | |
| ``` | |
| **5. 编译 curope** | |
| 在仓库根目录执行: | |
| ```bash | |
| cd third_party/ABot-Recon/abot_recon/modeling/pi3/models/curope | |
| pip install ninja | |
| python setup.py build_ext --inplace | |
| cd - | |
| ``` | |
| **6. 安装 requirement.txt** | |
| 在仓库根目录执行: | |
| ```bash | |
| pip install -r requirement.txt | |
| ``` | |