News for hackers. Stuff that matters.

A comment on Deep learning model compression methods. Parent comment

Re:Deep learning model compression methods by antixk on Monday April 05, 2021 @06:02AM (#26697114)
Becuase unless you have a certain (high) level of sparsity, sparse formats are infact ineffective in storing. There are cases where sparse formats take more memory than storing dense tensors.
[ Parent | on HN ]
Re:Deep learning model compression methods by posharma on Monday April 05, 2021 @06:24AM (#26697224)
Sure. It’s still one of the methods to compress models. You might be surprised how often the weights are really quite sparse.
[ Parent | on HN ]