search

DAMO-DI-ML / NeurIPS2023-One-Fits-All

The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"
445 stars 61 forks source link

Error when running Anomaly Detection task #7

Open Maath opened 10 months ago

Maath commented 10 months ago

I am trying to run the anomaly detection task on datasets like SMAP or MSL but I am getting the error RuntimeError: stack expects each tensor to be equal size, but got [100, 2] at entry 0 and [99, 2] at entry 29 . bellow is the Traceback , I appreciate your help in fixing this issue and thank you very much for your hard work.

Traceback (most recent call last): File "run.py", line 153, in exp.train(setting) File "/home/tfg/onefitsall/NeurIPS2023-One-Fits-All-main/Anomaly_Detection/exp/exp_anomaly_detection.py", line 115, in train test_loss = self.vali(test_data, test_loader, criterion) File "/home/tfg/onefitsall/NeurIPS2023-One-Fits-All-main/Anomaly_Detection/exp/exp_anomaly_detection.py", line 48, in vali for i, (batchx, ) in enumerate(vali_loader): File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 517, in next data = self._next_data() File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1199, in _next_data return self._process_data(data) File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1225, in _process_data data.reraise() File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/_utils.py", line 429, in reraise raise self.exc_type(msg) RuntimeError: Caught RuntimeError in DataLoader worker process 5. Original Traceback (most recent call last): File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 202, in _worker_loop data = fetcher.fetch(index) File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch return self.collate_fn(data) File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 83, in default_collate return [default_collate(samples) for samples in transposed] File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 83, in return [default_collate(samples) for samples in transposed] File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 63, in default_collate return default_collate([torch.as_tensor(b) for b in batch]) File "/opt/miniconda3/envs/onefitsall/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py", line 55, in default_collate return torch.stack(batch, 0, out=out) RuntimeError: stack expects each tensor to be equal size, but got [100, 2] at entry 0 and [99, 2] at entry 29

PSacfc commented 10 months ago

I cannot reproduce the error. The number of features for SMAP and MSL datasets should be 25 and 55, respectively. It seems that the feature number mentioned ("RuntimeError: stack expects each tensor to be equal size, but got [100, 2] at entry 0 and [99, 2] at entry 29") is 2. Please verify if you have downloaded the datasets correctly (https://github.com/thuml/Anomaly-Transformer).