search

zalandoresearch / pytorch-ts

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend
MIT License
1.21k stars 191 forks source link

A bug in Time-Grad-Electricity.ipynb #113

Closed UniqueRoHo closed 1 year ago

UniqueRoHo commented 1 year ago

Exception: Caught Exception in DataLoader worker process 0. Original Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 202, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 28, in fetch data.append(next(self.dataset_iter)) File "/usr/local/lib/python3.7/dist-packages/gluonts/transform/_base.py", line 104, in iter self.base_dataset, is_train=self.is_train File "/usr/local/lib/python3.7/dist-packages/gluonts/transform/_base.py", line 124, in call for data_entry in data_it: File "/usr/local/lib/python3.7/dist-packages/gluonts/transform/_base.py", line 124, in call for data_entry in data_it: File "/usr/local/lib/python3.7/dist-packages/gluonts/transform/_base.py", line 190, in call "Reached maximum number of idle transformation" Exception: Reached maximum number of idle transformation calls. This means the transformation looped over 1 inputs without returning any output. This occurred in the following transformation: gluonts.transform.split.InstanceSplitter(dummy_value=0.0, forecast_start_field="forecast_start", future_length=1, instance_sampler=gluonts.transform.sampler.ExpectedNumInstanceSampler(axis=-1, min_past=169, min_future=1, num_instances=1.0, total_length=130272, n=23), is_pad_field="is_pad", lead_time=0, output_NTC=True, past_length=169, start_field="start", target_field="target", time_series_fields=["time_feat", "observed_values"])

And my packages version as follow torch == 1.8.0 gluonts == 0.9.0

ken-take-it-so-so commented 1 year ago

Please try pip install gluonts==0.10.0

UniqueRoHo commented 1 year ago

Thanks a lot, it worked！