What is the difference between WeightNormSparsifier and torch.nn.utils.prune.l1_unstructured ?

[mayank64ce]

[supriyar]

cc @jcaip

[jcaip]

Hey @mayank64ce torch.nn.tils.prun.l1_unstructured is no longer maintained, so I would recommend using the WeightNormSparsifier. The sparsifier also allows for more configs, like block_size, or intra block sparsity.

Functionally however, they do the same thing - mask dense models to put zeros in the "right" place.

[mayank64ce]

I see, in the WeightNormSparsifier, there seem to be some additional parameters other different from l1_unstructured. How can I simulate the same behavior for a give prune_ratio .

Also can this sparse_block_shape parameter be of any arbitrary shape ?