EdgeConv

class dgNN.layers.EdgeConv(self, in_feats, out_feats, batch_norm=False)

EdgeConv layer from Dynamic Graph CNN for Learning on Point Clouds

\[h_{i}^{(l+1)}=\max _{j \in \mathcal{N}(i)}\left(\Theta \cdot\left(h_{j}^{(l)}-h_{i}^{(l)}\right)+\Phi \cdot h_{i}^{(l)}\right)\]
Parameters

  • in_feats (int) – input feature size.

  • out_feats (int) – output feature size.

  • batch_norm (bool) – whether to use batch normalization

forward(self, k, src_ind, feat):
Parameters

  • k (int) – number of edges per vertex.

  • src_ind (torch.tensor) – source index tensor of shape \((E)\), where \(E\) is the number of edges.

  • feat (torch.tensor) – the input feature of shape \((N,F_{in})\), where \(F_{in}\) is the input feature size.

Returns

the output feature of shape \((N, F_{out})\), where \(F_{out}\) is the output feature size.

Return type

torch.tensor