README.md 3.23 KB
Newer Older
fengzch-das's avatar
fengzch-das committed
1
2
3
# <div align="center"><strong>nerfacc</strong></div>
## 简介
NerfAcc 是一个基于PyTorch的NeRF训练与推理加速工具箱,其核心功能是通过优化辐射场体积渲染管线中的采样效率实现通用化加速,支持绝大多数NeRF模型的即插即用。
Matthew Tancik's avatar
Matthew Tancik committed
4

fengzch-das's avatar
fengzch-das committed
5
6
## 安装
组件支持组合
Ruilong Li's avatar
readme  
Ruilong Li committed
7

fengzch-das's avatar
fengzch-das committed
8
9
10
11
12
   | PyTorch版本 | fastpt版本  |nerfacc版本      | DTK版本                  | Python版本       | 推荐编译方式 |
   | ----------- | ----------- | ----------- | ------------------------ | -----------------| ------------ |
   | 2.5.1       | 2.1.0       |master       | >= 25.04                 | 3.8、3.10、3.11  | fastpt不转码 |
   | 2.4.1       | 2.0.1       |master       | >= 25.04                 | 3.8、3.10、3.11  | fastpt不转码 |
   | 其他        | 其他         | 其他        | 其他                     | 3.8、3.10、3.11  | hip转码      |
Ruilong Li(李瑞龙)'s avatar
Ruilong Li(李瑞龙) committed
13

fengzch-das's avatar
fengzch-das committed
14
+ pytorch版本大于2.4.1 && dtk版本大于25.04 推荐使用fastpt不转码编译。
Ruilong Li(李瑞龙)'s avatar
Ruilong Li(李瑞龙) committed
15

fengzch-das's avatar
fengzch-das committed
16
17
18
19
20
21
22
### 1、使用pip方式安装
nerfacc whl包下载目录:[光和开发者社区](https://download.sourcefind.cn:65024/4/main),选择对应的pytorch版本和python版本下载对应nerfacc的whl包
```shell
pip install torch* (下载torch的whl包)
pip install fastpt* --no-deps (下载fastpt的whl包)
source  /usr/local/bin/fastpt -E
pip install nerfacc* (下载的nerfacc的whl包)
23
```
fengzch-das's avatar
fengzch-das committed
24
### 2、使用源码编译方式安装
25

fengzch-das's avatar
fengzch-das committed
26
27
#### 编译环境准备
提供基于fastpt不转码编译:
Ruilong Li's avatar
readme  
Ruilong Li committed
28

fengzch-das's avatar
fengzch-das committed
29
1. 基于光源pytorch基础镜像环境:镜像下载地址:[光合开发者社区](https://sourcefind.cn/#/image/dcu/pytorch),根据pytorch、python、dtk及系统下载对应的镜像版本。
Ruilong Li(李瑞龙)'s avatar
Ruilong Li(李瑞龙) committed
30

fengzch-das's avatar
fengzch-das committed
31
32
33
34
35
36
2. 基于现有python环境:安装pytorch,fastpt whl包下载目录:[光合开发者社区](https://sourcefind.cn/#/image/dcu/pytorch),根据python、dtk版本,下载对应pytorch的whl包。安装命令如下:
```shell
pip install torch* (下载torch的whl包)
pip install fastpt* --no-deps (下载fastpt的whl包, 安装顺序,先安装torch,后安装fastpt)
pip install pytest
pip install wheel
Ruilong Li(李瑞龙)'s avatar
Ruilong Li(李瑞龙) committed
37
```
Ruilong Li(李瑞龙)'s avatar
Ruilong Li(李瑞龙) committed
38

fengzch-das's avatar
fengzch-das committed
39
40
41
42
#### 源码编译安装
- 代码下载
```shell
git clone http://developer.sourcefind.cn/codes/OpenDAS/nerfacc.git # 根据编译需要切换分支
Ruilong Li's avatar
readme  
Ruilong Li committed
43
```
fengzch-das's avatar
fengzch-das committed
44
- 提供2种源码编译方式(进入nerfacc目录):
Ruilong Li's avatar
Ruilong Li committed
45
```
fengzch-das's avatar
fengzch-das committed
46
47
1. 设置不转码编译环境变量
source /usr/local/bin/fastpt -C
Ruilong Li's avatar
Ruilong Li committed
48

fengzch-das's avatar
fengzch-das committed
49
50
51
2. 编译whl包并安装
python3 setup.py bdist_wheel
pip install dist/nerfacc* --no-deps
52

fengzch-das's avatar
fengzch-das committed
53
54
3. 源码编译安装
python3 setup.py install --no-deps
55
```
fengzch-das's avatar
fengzch-das committed
56
57
58
59
#### 注意事项
+ 若使用pip install下载安装过慢,可添加pypi清华源:-i https://pypi.tuna.tsinghua.edu.cn/simple/
+ ROCM_PATH为dtk的路径,默认为/opt/dtk
+ 在pytorch2.5.1环境下编译需要支持c++17语法,打开setup.py文件,把文件中的 -std=c++14 修改为 -std=c++17
60

fengzch-das's avatar
fengzch-das committed
61
## 验证
62
```
fengzch-das's avatar
fengzch-das committed
63
64
65
66
67
68
69
python3
Python 3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import nerfacc
>>> nerfacc.__version__
'0.5.3'
>>> 
70
```
fengzch-das's avatar
fengzch-das committed
71
版本号与官方版本同步,查询该软件的版本号;
72

fengzch-das's avatar
fengzch-das committed
73
74
## Known Issue
-
75

fengzch-das's avatar
fengzch-das committed
76
77
78
## 参考资料
- [README_ORIGIN](README_ORIGIN.md)
- [https://github.com/nerfstudio-project/nerfacc.git](https://github.com/nerfstudio-project/nerfacc.git)