new question!!
WIKI2020 opened this issue · 2 comments
WIKI2020 commented
Hello, the current situation is input [1 * 100] - > target [1 * 100], but if it is a CSV table, such as:
featuresA featuresB featuresC
2021/1/10 .........
2021/1/11 ........
2021/1/12 ...........
.......
So the input is BATCH * 3 * 100(3 features , 100timestep),how to change your code, thank you!
oliverguhr commented
Currently this code does not support multivariate predictions. You need to change the model in order to train a model on multiple features. PRs would be very welcome.
RuifMaxx commented
maybe you can rerfer to this one https://github.com/RuifMaxx/Multidimensional-time-series-with-transformer