René's URL Explorer Experiment

{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"Unable to run the code with error importing 'spmm'","articleBody":"Hi, I followed the instruction to reproduce results but had a problem with module 'spmm'. My torch version is 1.8.2, torchdrug is 0.1.2. Any ideas how to fix it?\r\n\r\n\u003e 12:53:15   Epoch 0 begin\r\nTraceback (most recent call last):\r\n  File \"script/run.py\", line 78, in \u003cmodule\u003e\r\n  File \"script/run.py\", line 30, in train_and_validate\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\core\\engine.py\", line 143, in train\r\n    loss, metric = model(batch)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torch\\nn\\modules\\module.py\", line 889, in _call_impl\r\n    result = self.forward(*input, **kwargs)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\tasks\\reasoning.py\", line 85, in forward\r\n    pred = self.predict(batch, all_loss, metric)\r\n  File \"C:\\Users\\Pengfei\\Documents\\cse research\\NBFNet-master\\nbfnet\\task.py\", line 288, in predict\r\n    pred = self.model(graph, h_index, t_index, r_index, all_loss=all_loss, metric=metric)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torch\\nn\\modules\\module.py\", line 889, in _call_impl\r\n    result = self.forward(*input, **kwargs)\r\n  File \"C:\\Users\\Pengfei\\Documents\\cse research\\NBFNet-master\\nbfnet\\model.py\", line 149, in forward\r\n    output = self.bellmanford(graph, h_index[:, 0], r_index[:, 0])\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\decorator.py\", line 232, in fun\r\n    return caller(func, *(extras + args), **kw)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\utils\\decorator.py\", line 56, in wrapper\r\n    return forward(self, *args, **kwargs)\r\n  File \"C:\\Users\\Pengfei\\Documents\\cse research\\NBFNet-master\\nbfnet\\model.py\", line 115, in bellmanford\r\n    hidden = layer(step_graph, layer_input)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torch\\nn\\modules\\module.py\", line 889, in _call_impl\r\n    result = self.forward(*input, **kwargs)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\layers\\conv.py\", line 91, in forward\r\n    update = self.message_and_aggregate(graph, input)\r\n  File \"C:\\Users\\Pengfei\\Documents\\cse research\\NBFNet-master\\nbfnet\\layer.py\", line 140, in message_and_aggregate\r\n    sum = functional.generalized_rspmm(adjacency, relation_input, input, sum=\"add\", mul=mul)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\layers\\functional\\spmm.py\", line 378, in generalized_rspmm\r\n    return Function.apply(sparse.coalesce(), relation, input)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\layers\\functional\\spmm.py\", line 172, in forward\r\n    forward = spmm.rspmm_add_mul_forward_cuda\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\utils\\torch.py\", line 27, in __getattr__\r\n    return getattr(self.module, key)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\utils\\decorator.py\", line 21, in __get__\r\n    result = self.func(obj)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torchdrug\\utils\\torch.py\", line 31, in module\r\n    return cpp_extension.load(self.name, self.sources, self.extra_cflags, self.extra_cuda_cflags,\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torch\\utils\\cpp_extension.py\", line 1079, in load\r\n    return _jit_compile(\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torch\\utils\\cpp_extension.py\", line 1317, in _jit_compile\r\n    return _import_module_from_library(name, build_directory, is_python_module)\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\site-packages\\torch\\utils\\cpp_extension.py\", line 1700, in _import_module_from_library\r\n    file, path, description = imp.find_module(module_name, [path])\r\n  File \"C:\\Users\\Pengfei\\anaconda3\\envs\\py38\\lib\\imp.py\", line 296, in find_module\r\n    raise ImportError(_ERR_MSG.format(name), name=name)\r\nImportError: No module named 'spmm'","author":{"url":"https://github.com/PengfeiHePower","@type":"Person","name":"PengfeiHePower"},"datePublished":"2022-03-31T17:04:49.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":3},"url":"https://github.com/7/NBFNet/issues/7"}