The input shape for LSTM

titu1994 / MLSTM-FCN

Multivariate LSTM Fully Convolutional Networks for Time Series Classification

482 stars 180 forks source link

Open mengshanfeng opened 3 years ago

mengshanfeng commented 3 years ago

Why the input shape for LSTM in Keras is not (Batchsize, Number of timesteps, Number of variables)?

jimmykimmy68 commented 3 years ago

Probably due to dimension shuffle?