bn Class Reference

Inheritance diagram for bn:

Public Member Functions
	__init__ (self, output_size, eps=1e-5, momentum=0.1, cross_replica=False, mybn=False)
	Constructor.
	forward (self, x)
	forward

Public Attributes
	output_size = output_size
	output size
	gain = P(torch.ones(output_size), requires_grad=True)
	Prepare gain and bias layers.
	bias = P(torch.zeros(output_size), requires_grad=True)
	bias
	eps = eps
	epsilon to avoid dividing by 0
	momentum = momentum
	Momentum.
	cross_replica = cross_replica
	Use cross-replica batchnorm?
	mybn = mybn
	Use my batchnorm?
	stored_mean = bias)
	stored_var
	training

Detailed Description

Normal, non-class-conditional BN

Definition at line 460 of file ieagan.py.

Constructor & Destructor Documentation

__init__()

__init__	(		self,
			output_size,
			eps = 1e-5,
			momentum = 0.1,
			cross_replica = False,
			mybn = False )

Constructor.

Definition at line 466 of file ieagan.py.

    ):
        super(bn, self).__init__()
        
        self.output_size = output_size
        
        self.gain = P(torch.ones(output_size), requires_grad=True)
        
        self.bias = P(torch.zeros(output_size), requires_grad=True)
        
        self.eps = eps
        
        self.momentum = momentum
        
        self.cross_replica = cross_replica
        
        self.mybn = mybn
 
        if mybn:
            self.bn = myBN(output_size, self.eps, self.momentum)
        # Register buffers if neither of the above
        else:
            self.register_buffer("stored_mean", torch.zeros(output_size))
            self.register_buffer("stored_var", torch.ones(output_size))
 

Member Function Documentation

forward()

forward	(		self,
			x )

forward

Definition at line 498 of file ieagan.py.

    def forward(self, x):
        if self.mybn:
            gain = self.gain.view(1, -1, 1, 1)
            bias = self.bias.view(1, -1, 1, 1)
            return self.bn(x, gain=gain, bias=bias)
        else:
            return F.batch_norm(
                x,
                self.stored_mean,
                self.stored_var,
                self.gain,
                self.bias,
                self.training,
                self.momentum,
                self.eps,
            )
 
 

Member Data Documentation

bias

bias = P(torch.zeros(output_size), requires_grad=True)

bias

Definition at line 480 of file ieagan.py.

bn

bn = myBN(output_size, self.eps, self.momentum)

Definition at line 491 of file ieagan.py.

cross_replica

cross_replica = cross_replica

Use cross-replica batchnorm?

Definition at line 486 of file ieagan.py.

eps

eps = eps

epsilon to avoid dividing by 0

Definition at line 482 of file ieagan.py.

gain

gain = P(torch.ones(output_size), requires_grad=True)

Prepare gain and bias layers.

Definition at line 478 of file ieagan.py.

momentum

momentum = momentum

Momentum.

Definition at line 484 of file ieagan.py.

mybn

mybn = mybn

Use my batchnorm?

Definition at line 488 of file ieagan.py.

output_size

output_size = output_size

output size

Definition at line 476 of file ieagan.py.

stored_mean

stored_mean = bias)

Definition at line 506 of file ieagan.py.

stored_var

stored_var

Definition at line 507 of file ieagan.py.

training

training

Definition at line 510 of file ieagan.py.

---

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

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