mindspore_gl.nn.EDGEConv

class mindspore_gl.nn.EDGEConv(in_feat_size: int, out_feat_size: int, batch_norm: bool, bias=True)[source]

EdgeConv layer. From the paper Dynamic Graph CNN for Learning on Point Clouds .

\[h_i^{(l+1)} = \max_{j \in \mathcal{N}(i)} ( \Theta \cdot (h_j^{(l)} - h_i^{(l)}) + \Phi \cdot h_i^{(l)})\]

\(\mathcal{N}(i)\) represents the neighbour node of \(i\). \(\Theta\) and \(\Phi\) represents linear layers.

Parameters

  • in_feat_size (int) – Input node feature size.

  • out_feat_size (int) – Output node feature size.

  • batch_norm (bool) – Whether use batch norm.

  • bias (bool, optional) – Whether use bias. Default: True.

Inputs:

  • x (Tensor): The input node features. The shape is \((N,*)\) where \(N\) is the number of nodes, and \(*\) could be of any shape.

  • g (Graph): The input graph.

Outputs:

  • Tensor, output node features. The shape is \((N, out\_feat\_size)\).

Raises

  • TypeError – If ‘in_feat_size’ is not a positive int.

  • TypeError – If ‘out_feat_size’ is not a positive int.

  • TypeError – If ‘batch_norm’ is not a bool.

  • TypeError – If ‘bias’ is not a bool.

Supported Platforms:

Ascend GPU

Examples

>>> import mindspore as ms
>>> from mindspore_gl.nn import EDGEConv
>>> from mindspore_gl import GraphField
>>> n_nodes = 4
>>> n_edges = 8
>>> feat_size = 16
>>> src_idx = ms.Tensor([0, 0, 0, 1, 1, 1, 2, 3], ms.int32)
>>> dst_idx = ms.Tensor([0, 1, 3, 1, 2, 3, 3, 2], ms.int32)
>>> ones = ms.ops.Ones()
>>> nodes_feat = ones((n_nodes, feat_size), ms.float32)
>>> graph_field = GraphField(src_idx, dst_idx, n_nodes, n_edges)
>>> out_size = 4
>>> conv = EDGEConv(feat_size, out_size, batch_norm=True)
>>> ret = conv(nodes_feat, *graph_field.get_graph())
>>> print(ret.shape)
(4, 4)