search

OdysseasKr / neural-disaggregator

Code for NILM experiments using Neural Networks. Uses Keras/Tensorflow and the NILMTK.
MIT License
138 stars 58 forks source link

prediction of the whole appliances #30

Open charlicruz opened 4 years ago

charlicruz commented 4 years ago

Hi, I found your project very interesting. Just a quick question.Is it possible to train and test the whole number of appliances (not only a single one)?. If it is possible, which command is used for doing and plot "ground_truth" and all the predicted appliances together? Thank you in advance Cheers

OdysseasKr commented 4 years ago

Hello! No it is not possible with this code. The models are used for inferring the consumption of a single device. If you want to do the same for several appliances with this architecture, you need to train a model for each one of them and use them separately.

charlicruz commented 4 years ago

Thanks a lot for you response. I can plot mains (in REDD) or aqggregate (in UKDALE) as the whole data building consumption. Why cannot I predict it as a single appliance? As you commented, the model is used for single devices but and I can model for each one. At this point, could it be possible to predict all these models together? many thanks in advance. Cheers