cogdl.utils

Module Contents

Classes

ArgClass

Functions

build_args_from_dict(dic)

add_self_loops(edge_index, edge_weight=None, fill_value=1, num_nodes=None)

add_remaining_self_loops(edge_index, edge_weight=None, fill_value=1, num_nodes=None)

row_normalization(num_nodes, edge_index, edge_weight=None)

symmetric_normalization(num_nodes, edge_index, edge_weight=None)

spmm(indices, values, b)

Args:

spmm_adj(indices, values, shape, b)

get_degrees(indices, num_nodes=None)

edge_softmax(indices, values, shape)

Args:

mul_edge_softmax(indices, values, shape)

Args:

remove_self_loops(indices)

get_activation(act)

cycle_index(num, shift)

batch_sum_pooling(x, batch)

batch_mean_pooling(x, batch)

tabulate_results(results_dict)

print_result(results, datasets, model_name)

set_random_seed(seed)

class cogdl.utils.ArgClass[source]

Bases: object

cogdl.utils.build_args_from_dict(dic)[source]
cogdl.utils.add_self_loops(edge_index, edge_weight=None, fill_value=1, num_nodes=None)[source]
cogdl.utils.add_remaining_self_loops(edge_index, edge_weight=None, fill_value=1, num_nodes=None)[source]
cogdl.utils.row_normalization(num_nodes, edge_index, edge_weight=None)[source]
cogdl.utils.symmetric_normalization(num_nodes, edge_index, edge_weight=None)[source]
cogdl.utils.spmm(indices, values, b)[source]

Args: indices : Tensor, shape=(2, E) values : Tensor, shape=(E,) shape : tuple(int ,int) b : Tensor, shape=(N, )

cogdl.utils.spmm_adj(indices, values, shape, b)[source]
cogdl.utils.get_degrees(indices, num_nodes=None)[source]
cogdl.utils.edge_softmax(indices, values, shape)[source]
Args:

indices: Tensor, shape=(2, E) values: Tensor, shape=(N,) shape: tuple(int, int)

Returns:

Softmax values of edge values for nodes

cogdl.utils.mul_edge_softmax(indices, values, shape)[source]
Args:

indices: Tensor, shape=(2, E) values: Tensor, shape=(E, d) shape: tuple(int, int)

Returns:

Softmax values of multi-dimension edge values for nodes

cogdl.utils.remove_self_loops(indices)[source]
cogdl.utils.get_activation(act)[source]
cogdl.utils.cycle_index(num, shift)[source]
cogdl.utils.batch_sum_pooling(x, batch)[source]
cogdl.utils.batch_mean_pooling(x, batch)[source]
cogdl.utils.tabulate_results(results_dict)[source]
cogdl.utils.print_result(results, datasets, model_name)[source]
cogdl.utils.set_random_seed(seed)[source]
cogdl.utils.args[source]