A question about Semisupervised_TU in pre_training

[ytpjh]

main.py 320
run_exp_benchmark()

main.py 278 run_exp_benchmark
run_exp_lib(create_n_filter_triples(datasets, feat_strs, nets,

main.py 183 run_exp_lib
cross_validation_with_val_set(

train_eval.py 115 cross_validation_with_val_set
train_loss, _ = train(

train_eval.py 234 train
out1 = model.forward_cl(data1)

res_gcn.py 173 forward_cl
return self.forward_BNConvReLU_cl(x, edge_index, batch, xg)

res_gcn.py 180 forward_BNConvReLU_cl
x_ = F.relu(conv(x_, edge_index))

module.py 1186 _call_impl
return forward_call(*input, **kwargs)

gcn_conv.py 103 forward
edge_index, norm = GCNConv.norm(

gcn_conv.py 90 norm
deg = scatter_add(edge_weight, row, dim=0, dim_size=num_nodes)

scatter.py 27 scatter_add
return scatter_sum(src, index, dim, out, dim_size)

scatter.py 9 scatter_sum
index = broadcast(index, src, dim)

utils.py 12 broadcast
src = src.expand(other.size())

RuntimeError:
expand(torch.cuda.LongTensor{[2, 12108]}, size=[12108]): the number of sizes provided (1) must be greater or equal to the number of dimensions in the tensor (2)

There is a error in scatter_add() function,this error remain that the size of src tensor is not euqal to the size of index tensor.I have tried many times but it is still not work.Could you give a solution about this question? Thanks

[yyou1996]

Hi @ytpjh,

The most possible reason for this issue would be the package version. Please follow https://github.com/Shen-Lab/GraphCL/tree/master/semisupervised_TU#dependencies to set up the environment.

If want to directly deal with this error, I would suggest starting from
res_gcn.py 180 forward_BNConvReLU_cl
x_ = F.relu(conv(x_, edge_index))

Expecially, print out x_.shape, edge_index.max(). It seems that edge_index.max() > x_.shape[0] which means you are trying to do message passing on non-existing nodes.