In this project, we make an attempt to investigate shapes of inputs and outputs, in various situations when feeding to RNNs, LSTMs, GRU. While creating RNN based models are important, understanding the shape transformations happening to the input and output gives us a better picture.
Even if we understand LSTMs theoretically, still many of us are confused about its input and output shapes while fitting the data to the network. This repo is for quickly experimenting various scenarios and checking shape transformations.