Description

Summary

• Convolutional LSTM for spatial forecasting In forecasting spatially-determined phenomena (the weather, say, or the next frame in a movie), we want to model temporal evolution, ideally using recurrence relations.
• Note how the channels dimension, which in the original input data would correspond to different variables, is creatively used to consolidate four convolutions into one: torch LSTM (non-stacked architecture) library(torch)# batch of 3, with 4 time steps each and a single feature# we will specify batch_first = TRUE when creating the LSTMinput<-torch_randn(c(3, 4, 1))input# default args# return shape = (batch_size, units)## note: For a single-layer GRU, these values are already provided in the first list item.gru(input) Reuse Text and figures are licensed under Creative Commons Attribution CC BY 4.0.