This repo contains some basic experiments in video prediction.
It contains a basic bouncing-balls video generator and an implementation of Convolutional RNN made by me. It also contains an implementation of Convolutional LSTM in PyTorch cloned from here, made by Andrea Palazzi and DavideA.
Please note that the ConvLSTM implements the following dynamics:
which is a bit different from the one in the original paper.
This is still a work in progress and is far from being perfect: if you find any bug please don't hesitate to open an issue.