search

graphdeeplearning / benchmarking-gnns

Repository for benchmarking graph neural networks
https://arxiv.org/abs/2003.00982
MIT License
2.5k stars 452 forks source link

When I run the superpixel graph_classification experiment, I got the error"'Column' object has no attribute 'deferred_dtype'" #77

Open weihai-98 opened 2 years ago

weihai-98 commented 2 years ago

Just as the title said, when I run the 'main_superpixels_graph_classification.py', I got the error"'Column' object has no attribute 'deferred_dtype'" in the file 'superpixels.py' when getting the feature of the graph data at lin290. line290for idx, graph in enumerate(graphs): line291 graphs[idx].ndata['feat'] = graph.ndata['feat'].float() line292 graphs[idx].edata['feat'] = graph.edata['feat'].float() line293batched_graph = dgl.batch(graphs) Unfortunately, I can't tackle this by myself. Have you encountered the same error? I indeed need your help. Thank you greatly! image

chaitjo commented 2 years ago

Hi @weihai-98, are you using the correct version of DGL? It may be that things have changed across new releases of DGL.