-
Thanks for sharing the codes, and the paper is great! I've noticed that this project is only an architecture of iTransformer, how can I train the model?
-
您好, 文章中的Q和K第一个维度分别为M和L为序列长度,根据itransformer,M和L是不是就是变量数或者是说节点数呢。
-
I notice that the official code script is using Miniformer, but the paper are comparing performance with iTransformer, which is not a fair comparision.
![image](https://github.com/user-attachments…
-
Hey Laowu, great work. However, i have a specific request, Can you please add the specific commands to run this code and where can we start with the implementation?
-
-
I predict for 1, 2, and 3 steps forward in time with the same lookback_len. Why predictions for first steps are different in all three predictions? It is the same point in time...
Do first prediction…
-
### What happened + What you expected to happen
无法使用样本内预测,阻止我完成接下来的任务
```
test.py 75
Y_hat_insample = nf.predict_insample(step_size=12)
core.py 1213 predict_insample
fcsts[:, col_idx : (col…
-
您好,我用itransformer跑预测,为什么mae 与 mape 相较于基准模型都更低,但 rmse 的值却比基准模型更高。这是为什么?如何才能使itransformer预测的rmse值降下来呢?使rmse评估指标也优于基准模型。望回复,十分感谢。
![image](https://github.com/user-attachments/assets/23a4e575-7469-4fb5-a…
-
### What happened + What you expected to happen
Traceback (most recent call last):
File "/data/anaconda3/envs/time_py/lib/python3.8/site-packages/streamlit/runtime/scriptrunner/script_runner.py", …
-
您好,
感谢您分享这篇论文以及相关代码和数据集资源!在使用过程中,我注意到以下情况,想请教您的看法:
问题描述
从论文中描述的数据划分表格(例如训练集、验证集、测试集的长度)来看,各部分数据长度加总后与原始数据集文件的总长度并不一致。这让我怀疑,是否您在使用过程中对数据集进行了筛选、清洗或某些预处理操作?
相关细节
例如:
原始数据集文件路径:electricity.csv…