liyyy2122 / tirgn Goto Github PK

I find the performance data of xERTE is from its paper, but the performance data of other models such as CyGNet and RE-NET is not clear. The two models(CyGNet and RE-NET) is not same with the paper of xERTE and RE-NET even preforms better than xERTE as it showed in your paper. I feel a bit confused about this.

Hi,

what is e-w-graph?
How can I generate it?

graph_file = os.path.join(dataset_path, '{}_stripped.nt.gz'.format(dataset_str))
task_file = os.path.join(dataset_path, 'completeDataset.tsv')
train_file = os.path.join(dataset_path, 'trainingSet.tsv')
test_file = os.path.join(dataset_path, 'testSet.tsv')

Thank you very much for sharing, Good job!
I encountered a problem while running the code, Could you give me some advice? Thank you very much!
I used the version as follows:
torch =1.6.0
torchvision = 0.7.0
dgl-cu102 = 0.5.2

Traceback (most recent call last):
File "main.py", line 564, in
run_experiment(args)
File "main.py", line 301, in run_experiment
loss_e, loss_r, loss_static = model.get_loss(history_glist, output[0], static_graph, one_hot_tail_seq, one_hot_rel_seq, use_cuda)
File "/home/shaowei.zhang/TiRGN/src/../src/rrgcn.py", line 240, in get_loss
evolve_embs, static_emb, r_emb, _, _ = self.forward(glist, static_graph, use_cuda)
File "/home/shaowei.zhang/TiRGN/src/../src/rrgcn.py", line 171, in forward
self.statci_rgcn_layer(static_graph, [])
File "/home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/shaowei.zhang/TiRGN/src/../rgcn/layers.py", line 59, in forward
self.propagate(g)
File "/home/shaowei.zhang/TiRGN/src/../rgcn/layers.py", line 171, in propagate
g.update_all(self.msg_func, fn.sum(msg='msg', out='h'), self.apply_func)
File "/home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/heterograph.py", line 4499, in update_all
ndata = core.message_passing(g, message_func, reduce_func, apply_node_func)
File "/home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/core.py", line 291, in message_passing
msgdata = invoke_edge_udf(g, ALL, g.canonical_etypes[0], mfunc, orig_eid=orig_eid)
File "/home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/core.py", line 73, in invoke_edge_udf
u, v, eid = graph.edges(form='all')
File "/home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/view.py", line 159, in call
return self._graph.all_edges(*args, **kwargs)
File "/home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/heterograph.py", line 3150, in all_edges
src, dst, eid = self._graph.edges(self.get_etype_id(etype), order)
File "/home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/heterograph_index.py", line 553, in edges
edge_array = _CAPI_DGLHeteroEdges(self, int(etype), order)
File "dgl/_ffi/_cython/./function.pxi", line 287, in dgl._ffi._cy3.core.FunctionBase.call
File "dgl/_ffi/_cython/./function.pxi", line 222, in dgl._ffi._cy3.core.FuncCall
File "dgl/_ffi/_cython/./function.pxi", line 211, in dgl._ffi._cy3.core.FuncCall3
File "dgl/_ffi/_cython/./base.pxi", line 155, in dgl._ffi._cy3.core.CALL
dgl._ffi.base.DGLError: [11:05:14] /opt/dgl/src/array/cuda/array_op_impl.cu:252: Check failed: e == cudaSuccess || e == cudaErrorCudartUnloading: CUDA kernel launch error: no kernel image is available for execution on the device
Stack trace:
[bt] (0) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x4f) [0x7f07b5ebea4f]
[bt] (1) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(dgl::runtime::NDArray dgl::aten::impl::Range<(DLDeviceType)2, long>(long, long, DLContext)+0x252) [0x7f07b66d83bb]
[bt] (2) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(dgl::aten::Range(long, long, unsigned char, DLContext)+0x1fd) [0x7f07b5e96c9d]
[bt] (3) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(dgl::UnitGraph::COO::Edges(unsigned long, std::string const&) const+0x9b) [0x7f07b668dcfb]
[bt] (4) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(dgl::UnitGraph::Edges(unsigned long, std::string const&) const+0xa1) [0x7f07b6688931]
[bt] (5) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(dgl::HeteroGraph::Edges(unsigned long, std::string const&) const+0x2a) [0x7f07b65b984a]
[bt] (6) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(+0xecdafc) [0x7f07b65c2afc]
[bt] (7) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/libdgl.so(DGLFuncCall+0x48) [0x7f07b6553f88]
[bt] (8) /home/anaconda3/envs/zhang_tkg/lib/python3.8/site-packages/dgl/_ffi/_cy3/core.cpython-38-x86_64-linux-gnu.so(+0x15f79) [0x7f07b3deef79]