.rst .pdf

mlreco.models.layers.gnn.encoders.cnn module

class mlreco.models.layers.gnn.encoders.cnn.ClustCNNMinkNodeEncoder(model_config, **kwargs)

Bases: torch.nn.modules.module.Module

CNN Node Encoder using MinkowskiEngine Backend

__init__(model_config, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(data, clusts)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

__module__ = 'mlreco.models.layers.gnn.encoders.cnn'

training: bool

class mlreco.models.layers.gnn.encoders.cnn.ClustCNNMinkEdgeEncoder(model_config, **kwargs)

Bases: torch.nn.modules.module.Module

Uses a CNN to produce node features for cluster GNN

__init__(model_config, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(data, clusts, edge_index)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

__module__ = 'mlreco.models.layers.gnn.encoders.cnn'

training: bool

mlreco.models.layers.gnn.encoders package mlreco.models.layers.gnn.encoders.geometric module