Model Class Reference

Class for the ConvNet generator model. More...

Inheritance diagram for Model:

Collaboration diagram for Model:

Public Member Functions
	__init__ (self)
	Constructor to create a new model instance.
	forward (self, z)
	Function to perform a forward pass.

Public Attributes
	fc = nn.Linear(96, 98304)
	Fully-connected layer.
	features
	Sequential composite layer.

Detailed Description

Class for the ConvNet generator model.

ConvNet generator model.

Definition at line 18 of file convnet.py.

Constructor & Destructor Documentation

__init__()

__init__

(

self

)

Constructor to create a new model instance.

Definition at line 23 of file convnet.py.

    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(96, 98304)
        self.features = nn.Sequential(
            # format: (channels, height, width)
            # (512, 8, 24)
            nn.Conv2d(512, 512, 5, 1, 2),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.Upsample(scale_factor=2, mode="nearest"),
            # (512, 16, 48)
            nn.Conv2d(512, 256, 5, 1, 2),
            nn.BatchNorm2d(256),
            nn.ReLU(inplace=True),
            nn.Upsample(scale_factor=2, mode="nearest"),
            # (256, 32, 96)
            nn.Conv2d(256, 128, 5, 1, 2),
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.Upsample(scale_factor=2, mode="nearest"),
            # (128, 64, 192)
            nn.Conv2d(128, 64, 5, 1, 2),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.Upsample(scale_factor=2, mode="nearest"),
            # (64, 128, 384)
            nn.Conv2d(64, 32, 5, 1, 2),
            nn.BatchNorm2d(32),
            nn.ReLU(inplace=True),
            nn.Upsample(scale_factor=2, mode="nearest"),
            # (32, 256, 768)
            nn.Conv2d(32, 1, 5, 1, 2),
            # (1, 256, 768)
        )
 

Member Function Documentation

forward()

forward	(		self,
			z )

Function to perform a forward pass.

Compute the model output for a given input.

Definition at line 60 of file convnet.py.

    def forward(self, z):
        """Compute the model output for a given input."""
        return self.features(self.fc(z).view(-1, 512, 8, 24)).tanh_()
 

Member Data Documentation

fc

fc = nn.Linear(96, 98304)

Fully-connected layer.

Definition at line 25 of file convnet.py.

features

features

Sequential composite layer.

Definition at line 26 of file convnet.py.

---

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

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