Comments (4)
Thank you for confirming the result @oguiza! Since ILI is a fairly small dataset, so the setting of drop_last can affect the result. I would think this will be diminished for larger datasets. But in any case, we should set the drop_last=False and we will fix that in the code.
from patchtst.
I discovered that a number of the performance gain in the supervised patchTST comes from using 'drop_last=True' for the test dataset.
With 'drop_last=False', for the ETTh1, Traffic, and Illness datasets, there was a drop in performance, while there was no drop for the Weather dataset.
I have not yet tested on the other datasets.
I think this can be a significant problem, as it would require the most of the tables in the paper to be rewritten and this could be considered as a cheating.
from patchtst.
Hi @oguiza, that is a great catch. Thank you very much! Our thought was to use the same setting in the dataloader they had for a fair comparison. But you are correct that setting drop_last=True will lead to the number of test samples not to be consistent with different choices of the batch size, although this difference may not cause a significant performance drop. We will change that setting in the code.
For self-supervised learning, we accidentally use the default drop_last=False which turns out to be the right choice, and the reported self-supervised results in the paper is for this setting.
from patchtst.
Thanks for your quick response @namctin.
I just run the script on the ILI dataset and the difference was significant in my opinion. If the performance with self-supervised is measured with all test samples as you say, this might indicate that the difference between supervised and self-supervised would be bigger than what's reflected in your paper. I'm sharing this just in case you want to investigate it further.
from patchtst.
Related Issues (20)
- how to use learner.distributed(), in self supervised pretrain code ?
- How does the visualization of Attention Weights organize the code? HOT 2
- scale
- RevIN and StandardScaler HOT 15
- Multivariate Time Series Classification HOT 6
- .
- Error during installation ”Could not find a version that satisfies the requirement numpy==1.21.3“,but the actual version is now 1.26.4
- Performance about self-supervised learning
- Can this model fit unbalanced panel data(more than one individual)?
- 请问论文中的注意力矩阵在代码里怎么输出
- Multivariate predict univariate HOT 2
- Stock Price Forecasting using PatchTST model HOT 4
- Pretrained Models in Huggingface Repository
- Question about not applying inverse_transform HOT 2
- Question about Table 9.
- outputs和batch_y 序列长度问题
- question about attention layer shared weight
- RuntimeError: required rank 4 tensor to use channels_last format
- How and where to save preds.npy and trues.npy after fine-tuning correctly?
- Why the train loss is higher than the validation and test?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from patchtst.