LTSF-Linear
LTSF-Linear copied to clipboard
cure-lab
[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"
Hello, I am having trouble reproducing some results for the DLinear model, could the authors please comment if something is wrong with the results for the datasets ETTh2 | datasets...
Hi, Thank you for this insightful paper and the code base. I had a question: Q1) I want to train the model (Transformer) with just pos embedding (as the original...
Dear all. Thanks for publishing and sharing such a nice and clean code and congrats for your nice paper. I want to reproduce the results of e.g Table 9 or...
I created my own sh file to run on my own dataset (4 features including the target) and I got this error File "LTSF-Linear/exp/exp_main.py", line 42, in _get_data data_set, data_loader...
when using the `Informer`model and a `pred_len == 1`, we observe an index error ``` IndexError: max(): Expected reduction dim 2 to have non-zero size ``` the reason, we believe,...
thanks for the great work. I can't reproduce the same results (e.g. dataset ILI) of NLinear as you presented in paper with CPUs, but i can get same results of...
As title, I can only find models saved after training in npy format and logs during training and pdf in test_result fold. So where is prediction results in csv format?
在论文中你提到half-ex实验是随机交换输入的前半部分和后半部分，请问你具体是如何实现随机的呢？如果可以的话，请你分享下half-ex的实验代码，谢谢。 此外，我按照你之前的回复中shuf实验的做法进行了复现，使用Linear在ETTh1数据集上的shuf实验结果和你很接近，但是在exchange数据集相差很大，不知道为什么。
Hello, I tried to run the default as in your instructions but got this error: RuntimeError: Given groups=1, weight of size [512, 7, 3], expected input[32, 8, 770] to have...
Hi, I tried to reproduce the result of the Repeat method and I did not find the same result as those displayed in your article for the ILI dataset. Your...
