SNEmbedding Class Reference

Inheritance diagram for SNEmbedding:

Public Member Functions
def	__init__ (self, num_embeddings, embedding_dim, padding_idx=None, max_norm=None, norm_type=2, scale_grad_by_freq=False, sparse=False, _weight=None, num_svs=1, num_itrs=1, eps=1e-12)
	Constructor.
def	forward (self, x)
	forward

Detailed Description

Embedding layer with spectral norm
We use num_embeddings as the dim instead of embedding_dim here
for convenience sake

Definition at line 799 of file ieagan.py.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			num_embeddings,
			embedding_dim,
			padding_idx = None,
			max_norm = None,
			norm_type = 2,
			scale_grad_by_freq = False,
			sparse = False,
			_weight = None,
			num_svs = 1,
			num_itrs = 1,
			eps = 1e-12
	)

Constructor.

Reimplemented from SN.

Definition at line 807 of file ieagan.py.

    ):
        nn.Embedding.__init__(
            self,
            num_embeddings,
            embedding_dim,
            padding_idx,
            max_norm,
            norm_type,
            scale_grad_by_freq,
            sparse,
            _weight,
        )
        SN.__init__(self, num_svs, num_itrs, num_embeddings, eps=eps)
 

Member Function Documentation

forward()

def forward	(		self,
			x
	)

forward

Definition at line 835 of file ieagan.py.

    def forward(self, x):
        return F.embedding(x, self.W_())
 
 

---

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

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