2021-06-13

PyG

• PyTorch geometric

• 图（Graph）是用于建立对象（节点）之间的成对关系，或者说是 “ 边关系 " 的模型。

https://pytorch-geometric.readthedocs.io/en/latest/

1.环境配置

conda create -n e python=3.8
conda activate e

conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c conda-forge

pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
pip install torch-geometric

2. 项目组织结构

./dataset/Cora/raw/...             # Cora引文数据集,未处理过的。
./dataset/Cora/processed/...       

./main.py

Data

构造函数

class Data(object):

    def __init__(self, x=None, edge_index=None, edge_attr=None, y=None, **kwargs):
        r"""
        Args:
            x (Tensor, optional): 节点属性矩阵，大小为`[num_nodes, num_node_features]`
            edge_index (LongTensor, optional): 边索引矩阵，大小为`[2, num_edges]`，第0行为尾节点，第1行为头节点，尾指向头
            edge_attr (Tensor, optional): 边属性矩阵，大小为`[num_edges, num_edge_features]`
            y (Tensor, optional): 节点或图的标签，任意大小（，其实也可以是边的标签）

        """
        self.x = x
        self.edge_index = edge_index
        self.edge_attr = edge_attr
        self.y = y

        for key, item in kwargs.items():
            if key == 'num_nodes':
                self.__num_nodes__ = item
            else:
                self[key] = item

类型转换

@classmethod
def from_dict(cls, dictionary):
    r"""Creates a data object from a python dictionary."""
    data = cls()
    for key, item in dictionary.items():
        data[key] = item

    return data

Dataset

from torch_geometric.datasets import Planetoid

dataset = Planetoid(root='/dataset', name='Cora')
# Cora()

len(dataset)
# 1

dataset.num_classes
# 7

dataset.num_node_features
# 1433