The most frequently used benchmark in time series classification/regression is the [UCR datasets](https://timeseriesclassification.com/), which consists of 128 time-series datasets. Both [sktime](https://www.sktime.net/en/stable/index.html) (a Tensorflow-based Python package) and [tsai](https://timeseriesai.github.io/tsai/) (a Pytorch-based Python package) have provided comprehensive solutions for data handling and model development, including the SoTA.

[Srijan2-0-2-3]

          The most frequently used benchmark in time series classification/regression is the [UCR datasets](https://timeseriesclassification.com/), which consists of 128 time-series datasets. Both [sktime](https://www.sktime.net/en/stable/index.html) (a Tensorflow-based Python package) and [tsai](https://timeseriesai.github.io/tsai/) (a Pytorch-based Python package) have provided comprehensive solutions for data handling and model development, including the SoTA.

Research regarding continual learning with time-series data using Avalanche has already been conducted. The research, titled "Continual Learning for Human State Monitoring", uses the WESAD dataset which is designed for wearable stress and affect detection. The coding information can be found at the following GitHub link: fexed/CLforHSM.

This article, "Continual Deep Learning for Time Series Modeling", provides a review of the ongoing development of CL for time series data.

Originally posted by @irosyadi in https://github.com/ContinualAI/avalanche/issues/1490#issuecomment-1706740578

[Srijan2-0-2-3]

In fexed/CLforHSM, when I run the code for wesad_train_test.py. I always get error as follows: Traceback (most recent call last): File "/home/srijan/PycharmProjects/CLforHSM/wesad_train_test.py", line 129, in train_wesad(strat,str(i)) File "/home/srijan/PycharmProjects/CLforHSM/wesad_train_test.py", line 39, in train_wesad scenario = dataset_benchmark( File "/home/srijan/.local/lib/python3.8/site-packages/avalanche/benchmarks/scenarios/generic_benchmark_creation.py", line 152, in create_multi_dataset_generic_benchmark make_classification_dataset( File "/home/srijan/.local/lib/python3.8/site-packages/avalanche/benchmarks/utils/classification_dataset.py", line 278, in make_classification_dataset targets_data: Optional[DataAttribute[TTargetType]] = _init_targets(dataset, targets) File "/home/srijan/.local/lib/python3.8/site-packages/avalanche/benchmarks/utils/classification_dataset.py", line 331, in _init_targets targets = _traverse_supported_dataset(dataset, _select_targets) File "/home/srijan/.local/lib/python3.8/site-packages/avalanche/benchmarks/utils/utils.py", line 346, in _traverse_supported_dataset raise initial_error File "/home/srijan/.local/lib/python3.8/site-packages/avalanche/benchmarks/utils/utils.py", line 284, in _traverse_supported_dataset result = values_selector(dataset, indices) File "/home/srijan/.local/lib/python3.8/site-packages/avalanche/benchmarks/utils/classification_dataset.py", line 913, in _select_targets raise ValueError( ValueError: Unsupported dataset: must have a valid targets field or has to be a Tensor Dataset with at least 2 Tensors

Is there any way to solve this issue.