real_models

Attributes

seed

Classes

Distmult	Base class for all neural network modules.
TransE	TransE trained with binary cross entropy
Tucker	Base class for all neural network modules.

Module Contents

real_models.seed = 1

class real_models.Distmult(param)

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

name = 'Distmult'

param

embedding_dim

num_entities

num_relations

loss

emb_ent_real

emb_rel_real

input_dp_ent_real

input_dp_rel_real

bn_ent_real

bn_rel_real

forward_head_batch(*, e1_idx, rel_idx)

forward_head_and_loss(e1_idx, rel_idx, targets)

init()

get_embeddings()

forward_triples(*, e1_idx, rel_idx, e2_idx)

forward_triples_and_loss(e1_idx, rel_idx, e2_idx, targets)

class real_models.TransE(param)

Bases: torch.nn.Module

TransE trained with binary cross entropy

name = 'TransE'

param

embedding_dim

num_entities

num_relations

emb_ent_real

emb_rel_real

gamma

loss

init()

get_embeddings()

forward_triples(*, e1_idx, rel_idx, e2_idx)

forward_triples_and_loss(e1_idx, rel_idx, e2_idx, target)

abstract forward_head_and_loss(*args, **kwargs)

class real_models.Tucker(param)

Bases: torch.nn.Module

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

name = 'Tucker'

param

embedding_dim

num_entities

num_relations

E

R

W

input_dropout

hidden_dropout1

hidden_dropout2

bn0

bn1

loss

init()

forward_head_batch(e1_idx, rel_idx)

forward_head_and_loss(e1_idx, rel_idx, targets)

get_embeddings()

abstract forward_triples(*args, **kwargs)

abstract forward_triples_and_loss(*args, **kwargs)