gnn_tracking.models.meta#

Wrappers and other “meta” models.

Classes#

Sequential

Sequentially apply modules for and take care of hyperparameters.

Functions#

obj_from_or_to_hparams(→ Any)

Used to support initializing python objects from hyperparameters:

Module Contents#

gnn_tracking.models.meta.obj_from_or_to_hparams(self: pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin, key: str, obj: Any) Any#

Used to support initializing python objects from hyperparameters: If obj is a python object other than a dictionary, its hyperparameters are saved (its class path and init args) to self.hparams[key]. If obj is instead a dictionary, its assumed that we have to restore an object based on this information.

class gnn_tracking.models.meta.Sequential(layers: list[torch.nn.Module])#

Bases: torch.nn.Module, pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin

Sequentially apply modules for and take care of hyperparameters.

forward(data: torch_geometric.data.Data) torch_geometric.data.Data#

Forward.