SN Class Reference

Inheritance diagram for SN:

Public Member Functions
	__init__ (self, num_svs, num_itrs, num_outputs, transpose=False, eps=1e-12)
	u (self)
	sv (self)
	W_ (self)

Public Attributes
	num_itrs = num_itrs
	Number of power iterations per step.
	num_svs = num_svs
	Number of singular values.
	transpose = transpose
	Transposed?
	eps = eps
	Epsilon value for avoiding divide-by-0.
bool	training
	Training mode flag (inherited from nn.Module).

Detailed Description

Spectral normalization base class

This base class expects subclasses to have a learnable weight parameter
(`self.weight`) as in `nn.Linear` or `nn.Conv2d`. It provides a method
to apply spectral normalization to that weight.

Attributes:
    num_svs (int): Number of singular values.
    num_itrs (int): Number of power iterations per step.
    transpose (bool): Whether to transpose the weight matrix.
    eps (float): Small constant to avoid divide-by-zero.
    u (list[Tensor]): Registered left singular vectors (buffers).
    sv (list[Tensor]): Registered singular values (buffers).
    training (bool): Inherited from nn.Module. True if in training mode.

Definition at line 226 of file ieagan.py.

Constructor & Destructor Documentation

__init__()

__init__	(		self,
			num_svs,
			num_itrs,
			num_outputs,
			transpose = False,
			eps = 1e-12 )

constructor

Definition at line 244 of file ieagan.py.

    def __init__(self, num_svs, num_itrs, num_outputs, transpose=False, eps=1e-12):
        """constructor"""
 
        super().__init__()
        ## Number of power iterations per step
        self.num_itrs = num_itrs
        ## Number of singular values
        self.num_svs = num_svs
        ## Transposed?
        self.transpose = transpose
        ## Epsilon value for avoiding divide-by-0
        self.eps = eps
        # Register a singular vector for each sv
        for i in range(self.num_svs):
            self.register_buffer(f"u{i:d}", torch.randn(1, num_outputs))
            self.register_buffer(f"sv{i:d}", torch.ones(1))
        ## Training mode flag (inherited from nn.Module). True if the module is in training mode.
        self.training: bool
 

Member Function Documentation

sv()

sv

(

self

)

Singular values
note that these buffers are just for logging and are not used in training.

Definition at line 271 of file ieagan.py.

    def sv(self):
        """
        Singular values
        note that these buffers are just for logging and are not used in training.
        """
        return [getattr(self, f"sv{i:d}") for i in range(self.num_svs)]
 

u()

u

(

self

)

Singular vectors (u side)

Definition at line 264 of file ieagan.py.

    def u(self):
        """
        Singular vectors (u side)
        """
        return [getattr(self, f"u{i:d}") for i in range(self.num_svs)]
 

W_()

W_

(

self

)

Compute the spectrally-normalized weight

Definition at line 278 of file ieagan.py.

    def W_(self):
        """
        Compute the spectrally-normalized weight
        """
        W_mat = self.weight.view(self.weight.size(0), -1)
        if self.transpose:
            W_mat = W_mat.t()
        # Apply num_itrs power iterations
        for _ in range(self.num_itrs):
            svs, _, _ = power_iteration(
                W_mat, self.u, update=self.training, eps=self.eps
            )
            # Update the svs
        if self.training:
            # Make sure to do this in a no_grad() context or you'll get memory leaks!  # noqa
            with torch.no_grad():
                for i, sv in enumerate(svs):
                    self.sv[i][:] = sv
        return self.weight / svs[0]
 
 

Member Data Documentation

eps

eps = eps

Epsilon value for avoiding divide-by-0.

Definition at line 255 of file ieagan.py.

num_itrs

num_itrs = num_itrs

Number of power iterations per step.

Definition at line 249 of file ieagan.py.

num_svs

num_svs = num_svs

Number of singular values.

Definition at line 251 of file ieagan.py.

training

bool training

Training mode flag (inherited from nn.Module).

True if the module is in training mode.

Definition at line 261 of file ieagan.py.

transpose

transpose = transpose

Transposed?

Definition at line 253 of file ieagan.py.

---

The documentation for this class was generated from the following file:

• pxd/scripts/pxd/background_generator/models/ieagan.py