NeRF Studio 使用Docker 安装记录

NerfStudio 使用Docker 安装记录

---

如果对你有帮助请点个赞吧~

---

安装过程

论文地址：https://arxiv.org/abs/2302.04264

1. 官方github安装文档 链接
2. 官网文档 链接
3. 安装 Docker
4. 安装 Nvidia 显卡驱动: Ubuntu18-22.04安装和干净卸载nvidia显卡驱动——超详细、最简单
5. 拉取官方Docker 镜像 链接
6. 创建容器

docker run --gpus all -u $(id -u) -v /folder/of/your/data:/workspace/ -v /home/<YOUR_USER>/.cache/:/home/user/.cache/ -p 7007:7007 --rm -it --shm-size=12gb  dromni/nerfstudio:<tag>  

7. 下载官方数据跑官方数据

从goole 云盘下载：链接

# Download some test data:
ns-download-data nerfstudio --capture-name=poster # 报错不存在文件夹

8. 解压文件夹poster_v3重新命名为poster放到data/nerfstudio/poster目录下
9. 输入命令开始训练

# Train model
ns-train nerfacto --data data/nerfstudio/poster

运行结果

出现下面界面表示模型开始训练：

在浏览器中输入终端显示的网址查看图像化结果

---

报错记录

1. 安装完显卡驱动后报错 终端输入： nvidia-smi

显示： Failed to initialize NVML: Driver/library version mismatch
NVML library version: 535.113

解决方案：驱动版本不匹配重装显卡驱动解决

2. 根据官方命令运行docker 报错

roboot@roboot-DK-ZHAN620:~/NerfDataset$ docker run --gpus all -u $(id -u) -v /home/roboot/NerfDataset:/workspace/ -v /home/roboot/.cache/:/home/user/.cache/ -p 7007:7007 --rm -it --shm-size=12gb dromni/nerfstudio:0.3.4 \   ns-process-data video --data /workspace/video.mp4   
docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]].

解决方案: docker gpu报错Error response from daemon: could not select device driver ““ with capabilities: [[gpu]]

3. 安装完nvidia docker 输入官方命令报错

roboot@roboot-DK-ZHAN620:~/NerfDataset$ docker run --gpus all  -v /home/roboot/NerfDataset:/workspace/ -v /home/roboot/.cache/:/home/user/.cache/ -p 7007:7007 --rm -it
--shm-size=12gb dromni/nerfstudio:0.3.3 \   ns-process-data video --data /workspace/video.mp4 
==========
== CUDA ==
========== 
CUDA Version 11.8.0 Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. This container image and its contents are governed by the NVIDIA Deep Learning Container License. By pulling and using the container, you accept the terms and conditions of this license: https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience. 
/opt/nvidia/nvidia_entrypoint.sh: line 67: exec:  : not found

解决方案： 百度后怀疑是docker run 命令输入有问题，删除命令中的 \ 符号

docker run --gpus all  -v /home/roboot/NerfDataset:/workspace/ -v /home/roboot/.cache/:/home/user/.cache/ -p 7007:7007 --rm -it
--shm-size=12gb dromni/nerfstudio:0.3.3    ns-process-data video --data /workspace/video.mp4 

感谢观看，如果对你有帮助请点个赞吧~