spandrel.architectures.__arch_helpers.dysample.DySample

class documentation

class DySample(nn.Module): (source)

Constructor: DySample(in_channels, out_ch, scale, groups, end_convolution)

View In Hierarchy

Adapted from 'Learning to Upsample by Learning to Sample': https://arxiv.org/abs/2308.15085 https://github.com/tiny-smart/dysample

Method __init__ Undocumented
Method forward Undocumented
Instance Variable end_conv Undocumented
Instance Variable end_convolution Undocumented
Instance Variable groups Undocumented
Instance Variable offset Undocumented
Instance Variable scale Undocumented
Instance Variable scope Undocumented
Method _init_pos Undocumented
def __init__(self, in_channels: int, out_ch: int, scale: int = 2, groups: int = 4, end_convolution: bool = True): (source)

Undocumented

def forward(self, x): (source)

Undocumented

end_conv = (source)

Undocumented

end_convolution = (source)

Undocumented

groups = (source)

Undocumented

offset = (source)

Undocumented

scale = (source)

Undocumented

scope = (source)

Undocumented

def _init_pos(self): (source)

Undocumented