THU-KEG / MetaKGR

Source codes and datasets for EMNLP 2019 paper "Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations"
115 stars 21 forks source link

RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED #1

Closed wutong8023 closed 5 years ago

wutong8023 commented 5 years ago

Traceback (most recent call last): File "/home/astone/anaconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/astone/anaconda3/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/astone/experiment/MetaKGR/src/experiments.py", line 811, in run_experiment(args) File "/home/astone/experiment/MetaKGR/src/experiments.py", line 792, in run_experiment train(lf) File "/home/astone/experiment/MetaKGR/src/experiments.py", line 255, in train lf.run_train(train_data, dev_data) File "/home/astone/experiment/MetaKGR/src/learn_framework.py", line 145, in run_train loss = self.loss(mini_batch) File "/home/astone/experiment/MetaKGR/src/emb/emb.py", line 103, in loss pred_scores = mdl.forward(e1, r, kg) File "/home/astone/experiment/MetaKGR/src/emb/fact_network.py", line 145, in forward stacked_inputs = self.bn0(stacked_inputs) File "/home/astone/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, **kwargs) File "/home/astone/anaconda3/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 83, in forward exponential_average_factor, self.eps) File "/home/astone/anaconda3/lib/python3.6/site-packages/torch/nn/functional.py", line 1697, in batch_norm training, momentum, eps, torch.backends.cudnn.enabled RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

Hi, would you please help me solve this problem? It appears when I try to run this command: ./experiment-emb.sh ./configs/fb15k-237-conve.sh --train 1

davidlvxin commented 5 years ago

It's a cuDNN error. Please make sure your computer has at least one GPU and pytorch with CUDA is installed successfully.