ICLR 2019 code

This release includes the code and data necessary to reproduce the results, as well as the checkpoints with weights of pre-trained networks in the ICLR 2019 paper:

Alexander S. Ecker, Fabian H. Sinz, Emmanouil Froudarakis, Paul G. Fahey, Santiago A. Cadena, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Andreas S. Tolias, Matthias Bethge: A rotation-equivariant convolutional neural network model of primary visual cortex. International Conference on Learning Representations (ICLR 2019), https://openreview.net/forum?id=H1fU8iAqKX.

To use the pre-trained networks or the data to train the networks, download the checkpoints attached to this release to the analysis/iclr2019 folder and extract them (they should reside in a checkpoints subfolder).