torch_geometric.nn.conv.DynamicEdgeConv

class DynamicEdgeConv(nn: Callable, k: int, aggr: str = 'max', num_workers: int = 1, **kwargs)[source]

The dynamic edge convolutional operator from the “Dynamic Graph CNN for Learning on Point Clouds” paper (see torch_geometric.nn.conv.EdgeConv), where the graph is dynamically constructed using nearest neighbors in the feature space.

Parameters:

nn (torch.nn.Module) – A neural network \(h_{\mathbf{\Theta}}\) that maps pair-wise concatenated node features x of shape :obj:`[-1, 2 * in_channels] to shape [-1, out_channels], e.g. defined by torch.nn.Sequential.
k (int) – Number of nearest neighbors.
aggr (str, optional) – The aggregation scheme to use ("add", "mean", "max"). (default: "max")
num_workers (int) – Number of workers to use for k-NN computation. Has no effect in case batch is not None, or the input lies on the GPU. (default: 1)
**kwargs (optional) – Additional arguments of torch_geometric.nn.conv.MessagePassing.

Shapes:

input: node features \((|\mathcal{V}|, F_{in})\) or \(((|\mathcal{V}|, F_{in}), (|\mathcal{V}|, F_{in}))\) if bipartite, batch vector \((|\mathcal{V}|)\) or \(((|\mathcal{V}|), (|\mathcal{V}|))\) if bipartite (optional)
output: node features \((|\mathcal{V}|, F_{out})\) or \((|\mathcal{V}_t|, F_{out})\) if bipartite

forward(x: Union[Tensor, Tuple[Tensor, Tensor]], batch: Union[Tensor, None, Tuple[Tensor, Tensor]] = None) → Tensor[source]: Runs the forward pass of the module.