Simplify: A Python library for optimizing pruned neural networks

Neural network pruning allows for impressive theoretical reduction of models sizes and complexity. However it usually offers little practical benefits as is most often limited to just zeroing out weights, without actually removing the pruned parameters. This precludes from actual advantages provided by sparsification methods. We propose Simplify, a PyTorch compatible library achieving effective model simplification. Simplified benefit both smaller memory footprint lower inference time, making their deployment embedded or mobile devices much more efficient.