Pytorch LSTMCell — shapes of input, hidden state and cell state

PyTorch LSTMCell — Shapes of Input, Hidden State, Cell State And Output

In Pytorch, to use an LSTMCell (with nn.LSTMCell), we need to understand how the tensors representing the input time series, hidden state vector, and cell state vector should be shaped. In this article, let us assume you are working with multivariate time series. Each multivariate time series in the dataset contains multiple univariate time series.

In this article, we use the following terminology,

batch = number …

article hidden lstm machine learning neural-network-algorithm pytorch recurrent neural network series state time series vector