Pruning doesn't affect speed nor memory for Resnet-101

[Michela (Michela Paganini)]

@ra_schoonhoven’s answer is correct. For more information, see my answer to a similar question (+ links therein):

Weight Pruning on BERT

The point of PyTorch pruning, at the moment, is not necessarily to guarantee inference time speedups or memory savings. It’s more of an experimental feature to enable pruning research. In any case, answers to questions similar to yours were given here and here. TL;DR: You can save space by calling .to_sparse() which brings your sparse tensor into coordinate representation. You cannot expect any inference speedups unless you use a custom sparse matrix algebra library to power your computation. t…