torch.nn.utils.prune.remove¶

torch.nn.utils.prune.remove(module, name)[source]¶

Removes the pruning reparameterization from a module and the pruning method from the forward hook. The pruned parameter named name remains permanently pruned, and the parameter named name+'_orig' is removed from the parameter list. Similarly, the buffer named name+'_mask' is removed from the buffers.

Note

Pruning itself is NOT undone or reversed!

Parameters

• module (nn.Module) – module containing the tensor to prune

• name (str) – parameter name within module on which pruning will act.

Examples

>>> m = random_unstructured(nn.Linear(5, 7), name='weight', amount=0.2)
>>> m = remove(m, name='weight')