jxchen01/ConvLSTM

ConvLSTM

Source code associated with Spatio-temporal video autoencoder with differentiable memory, submitted to ICLR2016.

This is a demo version to be trained on our modified version of moving MNIST dataset, available here. Some videos obtained on real test sequences are also available here.

Dependencies

• rnn: our code extends rnn by providing a spatio-temporal convolutional version of LSTM cells.
• extracunn: contains cuda code for SpatialConvolutionalNoBias layer and Huber gradient computation.
• stn.