dtchang
dtchang
3.6.1
In Python 3.6 I tried: _charset = np.string__(charset) It did away: _TypeError: No conversion path for dtype: dtype('
One way to resolve the exception is to checkout / download / replace the data files.
I tried using the PyTorch Geometric implementation, dense_diff_pool(). When A contains edge attributes as an additional dimension, the following computation (using torch.matmul()) throws an exception: A(l+1)=S(l)^A(l)S(l), where S(l)^ is the...
When A contains multiple edge attributes (many datasets, including mine, have such), its size is num_nodes x num_nodes x num_edge_attrs. I also reported this as an issue with PyG. The...
Per your suggestion, I made the following changes in dense_diff_pool(): if adj.dim() == 3: out_adj = torch.matmul(torch.matmul(s.transpose(1, 2), adj), s) else: # adj.dim() == 4 adj_perm = adj.permute(0, 3, 1,...
The following changes do away RuntimeError: if adj.dim() == 4: adj = adj.unbind(3)[0] This would produce good link_loss if the first edge attribute (type) is edge weight. Is there a...
Do you have plans for this? If so, what is the time frame? In any case, for quantum graph kernels, can you suggest what encoding circuits (implemented, new) to use?...
add_nodes_to_edges(edge_dict, inplace=True) has modify / add_new semantics, depending on whether edge_id in edge_dict already exists or not. We need a method with add_new semantics such that if edge_id already exists,...
Withdraw request.