# <div align="center"><strong>torch-spline-conv-1.2.1</strong></div>
## 简介
torch-spline-conv是基于PyTorch框架的一个软件包，用于实现图卷积神经网络中的Spline卷积操作。图卷积神经网络是一种能够在图结构数据上进行深度学习的模型，适用于节点分类、图分类和图生成等任务。

## 依赖安装
+ pytorch1.10或者pytorch1.13 以及对应的torchvision（建议dtk-22.04.2、dtk-23.04与dtk-23.10）
+ python 3.7-3.10

### 1、使用源码编译方式安装

#### 编译环境准备
提供2种环境准备方式：

1. 基于光源pytorch基础镜像环境：镜像下载地址：[https://sourcefind.cn/#/image/dcu/pytorch](https://sourcefind.cn/#/image/dcu/pytorch)，根据pytorch、python、dtk及系统下载对应的镜像版本。

2. 基于现有python环境：安装pytorch和torchvision，whl包下载目录：[https://cancon.hpccube.com:65024/4/main/pytorch](https://cancon.hpccube.com:65024/4/main/pytorch)，[https://cancon.hpccube.com:65024/4/main/vision](https://cancon.hpccube.com:65024/4/main/vision)，根据python、dtk版本,下载对应pytorch和torchvision的whl包。安装命令如下：
```shell
pip install torch* (下载的torch的whl包)
pip install torchvision* (下载的torchvision的whl包)
pip install setuptools==59.5.0 wheel
```

#### 源码编译安装
- 代码下载
```shell
git clone http://developer.hpccube.com/codes/aicomponent/torch-spline-conv # 根据编译需要切换分支
```
- 源码编译（进入torch-spline-conv目录）：
```
export C_INCLUDE_PATH=/public/software/apps/DeepLearning/PyTorch_Lib/gflags-2.1.2-build/include:$C_INCLUDE_PATH
export CPLUS_INCLUDE_PATH=/public/software/apps/DeepLearning/PyTorch_Lib/gflags-2.1.2-build/include:$CPLUS_INCLUDE_PATH
export C_INCLUDE_PATH=/public/software/apps/DeepLearning/PyTorch_Lib/glog-build/include:$C_INCLUDE_PATH
export CPLUS_INCLUDE_PATH=/public/software/apps/DeepLearning/PyTorch_Lib/glog-build/include:$CPLUS_INCLUDE_PATH
export C_INCLUDE_PATH=$ROCM_PATH/rocrand/include:$C_INCLUDE_PATH
export CPLUS_INCLUDE_PATH=$ROCM_PATH/rocrand/include:$CPLUS_INCLUDE_PATH
export LD_LIBRARY_PATH=$ROCM_PATH/rocrand/lib:$LD_LIBRARY_PATH
export FORCE_ONLY_HIP=1
export CC=hipcc
export CXX=hipcc

python setup.py install
```
#### 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

## 验证

```python
import torch
from torch_spline_conv import spline_conv

x = torch.rand((4, 2), dtype=torch.float)  # 4 nodes with 2 features each
edge_index = torch.tensor([[0, 1, 1, 2, 2, 3], [1, 0, 2, 1, 3, 2]])  # 6 edges
pseudo = torch.rand((6, 2), dtype=torch.float)  # two-dimensional edge attributes
weight = torch.rand((25, 2, 4), dtype=torch.float)  # 25 parameters for in_channels x out_channels
kernel_size = torch.tensor([5, 5])  # 5 parameters in each edge dimension
is_open_spline = torch.tensor([1, 1], dtype=torch.uint8)  # only use open B-splines
degree = 1  # B-spline degree of 1
norm = True  # Normalize output by node degree.
root_weight = torch.rand((2, 4), dtype=torch.float)  # separately weight root nodes
bias = None  # do not apply an additional bias

out = spline_conv(x, edge_index, pseudo, weight, kernel_size,
                  is_open_spline, degree, norm, root_weight, bias)

print(out.size())
torch.Size([4, 4])  # 4 nodes with 4 features each
```

## Known Issue
- 该库没有基于cpu环境修改，仅支持dcu，请在有dcu卡的环境运行。
- 如需完整使用所有pyg功能，请pip install torch-geometric

## 参考资料
- [README_ORIGIN](README_ORIGIN.md)
- [https://pypi.org/project/torch-sparse/0.6.13/](https://pypi.org/project/torch-sparse/0.6.13/)