✳flâneur — a map of the web's best reading

torch_geometric.utils — pytorch_geometric documentation

pytorch-geometric.readthedocs.io · 18,544 words · saved by 1 readers

Reduces all values from the src tensor at the indices specified in the index tensor along a given dimension dim. group_argsort Returns the indices that sort the tensor src along a given dimension in ascending order by value. segment Reduces all values in the first dimension of the src tensor within the ranges specified in the ptr. index_sort Sorts the elements of the inputs tensor in ascending order. cumsum Returns the cumulative sum of elements of x. degree Computes the (unweighted) degree of a given one-dimensional index tensor. softmax Computes a sparsely evaluated softmax. lexsort Performs an indirect stable sort using a sequence of keys. sort_edge_index Row-wise sorts edge_index. coalesce Row-wise sorts edge_index and removes its duplicated entries. is_undirected Returns True if the graph given by edge_index is undirected. to_undirected Converts the graph given by edge_index to an undirected graph such that ( 𝑗 , 𝑖 ) ∈ 𝐸 for every edge ( 𝑖 , 𝑗 ) ∈ 𝐸 . contains_self_loops

torch_geometric.utils - pytorch_geometric documentation --> torch_geometric.utils Edit on GitHub torch_geometric.utils  scatter Reduces all values from the src tensor at the indices specified in the index tensor along a given dimension dim . group_argsort Returns the indices that sort the tensor src along a given dimension in ascending order by value. segment Reduces all values in the first dimension of the src tensor within the ranges specified in the ptr . index_sort Sorts the elements of the inputs tensor in ascending order. cumsum Returns the cumulative sum of elements of x . degree Compu

Explore this link on the map →

related reading