Question about model used in RNN

OdysseasKr / neural-disaggregator

Code for NILM experiments using Neural Networks. Uses Keras/Tensorflow and the NILMTK.

MIT License

138 stars 57 forks source link

Question about model used in RNN #24

Closed Hessen525 closed 4 years ago

Hessen525 commented 4 years ago

Hi, I have some question as described as following,

after 1D Conv, the shape change from (1,1) to (1,16), is that means that each input value changed to (1,16)? besides, Could you please give me more detail about how the first LSTM work? ex: How many step numbers here etc.

I am so confused, Thanks!

OdysseasKr commented 4 years ago

Hi Hessen. The shape is changed from (1,1) to (1,16) because the convolutional layer has 16 filters (first argument). So, you are right, each input value is changes to (1,16). Maybe this visualization helps.

I would not be qualified to explain LSTM to be honest, but this article was very helpful to me. :)