search

thuml / AutoTimes

Official implementation for "AutoTimes: Autoregressive Time Series Forecasters via Large Language Models"
https://arxiv.org/abs/2402.02370
MIT License
38 stars 3 forks source link

Encountering Error When Running AutoTimes_M4.sh #5

Closed shisi-cc closed 1 month ago

shisi-cc commented 2 months ago

When I run sh scripts/time_series_forecasting/short_term/AutoTimes_M4.sh, I encounter the following error. How can I resolve this?

Traceback (most recent call last): File "/data/work/TimeLLM/AutoTimes/run.py", line 124, in exp.train(setting) File "/data/work/TimeLLM/AutoTimes/exp/exp_short_term_forecasting.py", line 60, in train train_data, train_loader = self._get_data(flag='train') ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/work/TimeLLM/AutoTimes/exp/exp_short_term_forecasting.py", line 34, in _get_data data_set, data_loader = data_provider(self.args, flag) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/data/work/TimeLLM/AutoTimes/data_provider/data_factory.py", line 32, in data_provider data_set = Data( ^^^^^ File "/data/work/TimeLLM/AutoTimes/data_provider/data_loader.py", line 247, in init self.read_data() File "/data/work/TimeLLM/AutoTimes/data_provider/data_loader.py", line 255, in read_data training_values = np.array( ^^^^^^^^^ ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (414,) + inhomogeneous part.

hvlgo commented 1 month ago

We implemented our repository based on time-series-library. You can refer to this to solve this problem.