Jiawei Jiang

> 你好，这篇论文的编号是多少呢？ 我在复现论文57，CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting。也遇到了这个问题，无法创建复数类型的参数。 【repo链接】：https://github.com/aptx1231/CoST_Paddle

【队名】：aptx1231 【序号】：兴10 【论文】：CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting 【状态】：报名&提交 【repo链接】：https://github.com/aptx1231/CoST_Paddle

Do you mean prediction with a trained model? You need to specify two parameters, one is `--train False`, which controls the code to test directly without training. The other is...

What does "1 sample" mean?

Modify the parameters `input_window` and `output_window` to change the length of input and output.

> Do you mean prediction with a trained model? You need to specify two parameters, one is `--train False`, which controls the code to test directly without training. The other...

This requires processing the data into atomic files before libcity can be used.

You can run the model directly with `run_model.py`, --train false and --exp_id ID to specify the location of the pre-trained model to apply the pre-trained model to the new data.

test_model.py only takes a batch data for testing, it can't achieve your requirement

`T_DRIVE20150206.zip` is also a traffic flow dataset, not a trajectory dataset, the same as `T_DRIVE_SMALL`. If you need to match the original T-Drive trajectory data to the road network, you...