liyyy2122 / tirgn Goto Github PK
View Code? Open in Web Editor NEWCode of TiRGN
Code of TiRGN
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]
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.