nn package

Submodules

nn.dataloader module

class nn.dataloader.BidirectionalOneShotIterator(dataloader_head, dataloader_tail, dataloader_neg=None, neg_ratio=1)

Bases: object

ZincBase uses this class automatically when you want to train a model from a KB.

next_no_neg()

next_with_neg()

static one_shot_iterator(dataloader)

class nn.dataloader.NegDataset(neg_triples)

Bases: sphinx.ext.autodoc.importer._MockObject

Zincbase sets this up automatically from the knowledge base. It’s a generator used for negative examples.

class nn.dataloader.TrainDataset(triples, nrelation, negative_sample_size, mode)

Bases: sphinx.ext.autodoc.importer._MockObject

Zincbase sets this up automatically from the knowledge base. It’s the generator for the RotatE algorithm.

static collate_fn(data)

static count_frequency(triples, start=4)

static get_true_attr(triples)

static get_true_head_and_tail(triples)

nn.rotate module

class nn.rotate.KGEModel(model_name, nentity, nrelation, hidden_dim, gamma, double_entity_embedding=False, double_relation_embedding=False, node_attributes=[], pred_attributes=[], attr_loss_to_graph_loss=1.0, pred_loss_to_graph_loss=1.0, device='cuda')

Bases: sphinx.ext.autodoc.importer._MockObject

ComplEx(head, relation, tail, mode)

RotatE(head, relation, tail, mode)

forward(sample, mode='single', attributes=True, predict_pred_prop=False, predict_only=False)

A single forward pass

run_embedding(embedding, attribute_name)

static train_step(model, optimizer, train_iterator, args)

Module contents