torch_geometric.nn.models.NeuralFingerprint

class NeuralFingerprint(in_channels: int, hidden_channels: int, out_channels: int, num_layers: int, **kwargs)

Bases: Module

来自“Convolutional Networks on Graphs for Learning Molecular Fingerprints”论文的神经指纹模型，用于生成分子的指纹。

Parameters:

• in_channels (int) – Size of each input sample.

• hidden_channels (int) – Size of each hidden sample.

• out_channels (int) – 每个输出指纹的大小。

• num_layers (int) – 层数。

• **kwargs (可选) – torch_geometric.nn.conv.MFConv 的额外参数。

forward(x: Tensor, edge_index: Union[Tensor, SparseTensor], batch: Optional[Tensor] = None, batch_size: Optional[int] = None) → Tensor

Return type:

Tensor

reset_parameters()

重置模块的所有可学习参数。