Shortcuts

LnStructured

class torch.nn.utils.prune.LnStructured(amount, n, dim=-1)[source]

Prune entire (currently unpruned) channels in a tensor based on their Ln-norm.

Parameters
  • amount (int or float) – quantity of channels to prune. If float, should be between 0.0 and 1.0 and represent the fraction of parameters to prune. If int, it represents the absolute number of parameters to prune.

  • n (int, float, inf, -inf, 'fro', 'nuc') – See documentation of valid entries for argument p in torch.norm().

  • dim (int, optional) – index of the dim along which we define channels to prune. Default: -1.

classmethod apply(module, name, amount, n, dim)[source]

Adds the forward pre-hook that enables pruning on the fly and the reparametrization of a tensor in terms of the original tensor and the pruning mask.

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

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

  • amount (int or float) – quantity of parameters to prune. If float, should be between 0.0 and 1.0 and represent the fraction of parameters to prune. If int, it represents the absolute number of parameters to prune.

  • n (int, float, inf, -inf, 'fro', 'nuc') – See documentation of valid entries for argument p in torch.norm().

  • dim (int) – index of the dim along which we define channels to prune.

apply_mask(module)

Simply handles the multiplication between the parameter being pruned and the generated mask. Fetches the mask and the original tensor from the module and returns the pruned version of the tensor.

Parameters

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

Returns

pruned version of the input tensor

Return type

pruned_tensor (torch.Tensor)

compute_mask(t, default_mask)[source]

Computes and returns a mask for the input tensor t. Starting from a base default_mask (which should be a mask of ones if the tensor has not been pruned yet), generate a mask to apply on top of the default_mask by zeroing out the channels along the specified dim with the lowest Ln-norm.

Parameters
  • t (torch.Tensor) – tensor representing the parameter to prune

  • default_mask (torch.Tensor) – Base mask from previous pruning iterations, that need to be respected after the new mask is applied. Same dims as t.

Returns

mask to apply to t, of same dims as t

Return type

mask (torch.Tensor)

Raises

IndexError – if self.dim >= len(t.shape)

prune(t, default_mask=None)

Computes and returns a pruned version of input tensor t according to the pruning rule specified in compute_mask().

Parameters
  • t (torch.Tensor) – tensor to prune (of same dimensions as default_mask).

  • default_mask (torch.Tensor, optional) – mask from previous pruning iteration, if any. To be considered when determining what portion of the tensor that pruning should act on. If None, default to a mask of ones.

Returns

pruned version of tensor t.

remove(module)

Removes the pruning reparameterization from a module. 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!

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources