search

shunyaoshih / TPA-LSTM

Temporal Pattern Attention for Multivariate Time Series Forecasting
699 stars 187 forks source link

What's the assert self.para.highway == self.para.attention_len means in data_generator #9

Open Kitaharakasusa opened 4 years ago

Kitaharakasusa commented 4 years ago

when I change the data set to electricity and train, it will report a error by the assert self.para.highway == self.para.attention_len , but when I delete this line, it will run but report the input can not be empty? I don't understand the relationship between the parameter highway and attention_len , could you please give me some help? thanks a lot.

Franzis39 commented 4 years ago

Same problem here, in general I would love to test this model for my own data, is there an easy way to do this ?

Giuseppedella commented 4 years ago

has anyone managed to change the data at the end?

Kitaharakasusa commented 4 years ago

has anyone managed to change the data at the end?

I have tried to change the data, but I haven't finished it, my data is multiple variables to predict one, but this code is multiple to multiple, it's difficult to change it to me, by the way, change the value of highway and attention_len to the same, the code can run.

ronykrell commented 4 years ago

Same, also, my data is multivariate time series for different people - so I have a p x n x d dataset - for example values for 25 heart rate sensors for 300 time steps for 50 people. The MTS examples like electricity consumption are n x d (e.g. 25 sensors for 300 time steps)