复现vectornet遇到的报错

1.TypeError: inc() takes 3 positional arguments but 4 were given
解决方案参考了博客https://blog.csdn.net/weixin_44861304/article/details/130833495
将site-pacakages/torch_geometric/data/collate.py/get_incs（源文件）中def get_incs()方法按照如下方式修改：

def get_incs(key, values: List[Any], data_list: List[BaseData],
             stores: List[BaseStorage]) -> Tensor:
    repeats = [
        data.__inc__(key, value)
        for value, data, store in zip(values, data_list, stores)
    ]
    if isinstance(repeats[0], Tensor):
        repeats = torch.stack(repeats, dim=0)
    else:
        repeats = torch.tensor(repeats)
    return cumsum(repeats[:-1])

2. AttributeError: Can’t get attribute ‘GraphData’ on <module ‘main’ from ‘’>

解决方案：需要把自定义的那个模型的类倒进来
找到GraphData所在的文件，在dataset文件内，所以在代码头部加上：
from dataset import GraphData

from dataset import GraphData