The implementation of Normalized Cross Correlation Layer, which is proposed by Dosovitskiy et al.[1], on Keras with tensorflow backend.
"NormalizedCrossCorrelation.py" contains the code of the layer and an simple example of how to use it.
[1] Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., ... & Brox, T. (2015). Flownet: Learning optical flow with convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2758-2766).