search

lrjconan / GRAN

Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019
MIT License
469 stars 96 forks source link

Got an error message in running the test of experiments 'grad_grid' #6

Open reasonance1216 opened 4 years ago

reasonance1216 commented 4 years ago

After training model using grid database, I got a following message like..

File "run_exp.py", line 40, in main runner.test() File "/home/reasonance1216/GRAN-master/runner/gran_runner.py", line 334, in test A_tmp = model(input_dict) File "/home/reasonance1216/anaconda3/envs/wavernn/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, kwargs) File "/home/reasonance1216/anaconda3/envs/wavernn/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 141, in forward return self.module(*inputs[0], *kwargs[0]) File "/home/reasonance1216/anaconda3/envs/wavernn/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(input, kwargs) File "/home/reasonance1216/GRAN-master/model/gran_mixture_bernoulli.py", line 445, in forward A = self._sampling(batch_size) File "/home/reasonance1216/GRAN-master/model/gran_mixture_bernoulli.py", line 292, in _sampling A = torch.tril(A, diagonal=-1) RuntimeError: invalid argument 1: expected a matrix at /opt/conda/conda-bld/pytorch_1544174967633/work/aten/src/THC/generic/THCTensorMathPairwise.cu:174

I haven't modified the source code at all. Is there anybody who are having same problem with me?

lrjconan commented 4 years ago

It may be caused by the fact that your PyTorch version is low so that tril does not have batch mode, c.f., this issue.