LazyConvTranspose2d#

classtorch.nn.modules.conv.LazyConvTranspose2d(out_channels,kernel_size,stride=1,padding=0,output_padding=0,groups=1,bias=True,dilation=1,padding_mode='zeros',device=None,dtype=None)[source]#

Atorch.nn.ConvTranspose2d module with lazy initialization of thein_channels argument.

Thein_channels argument of theConvTranspose2d is inferred fromtheinput.size(1).The attributes that will be lazily initialized areweight andbias.

Check thetorch.nn.modules.lazy.LazyModuleMixin for further documentationon lazy modules and their limitations.

Parameters

• out_channels (int) – Number of channels produced by the convolution

• kernel_size (int ortuple) – Size of the convolving kernel

• stride (int ortuple,optional) – Stride of the convolution. Default: 1

• padding (int ortuple,optional) –dilation*(kernel_size-1)-padding zero-paddingwill be added to both sides of each dimension in the input. Default: 0

• output_padding (int ortuple,optional) – Additional size added to one sideof each dimension in the output shape. Default: 0

• groups (int,optional) – Number of blocked connections from input channels to output channels. Default: 1

• bias (bool,optional) – IfTrue, adds a learnable bias to the output. Default:True

• dilation (int ortuple,optional) – Spacing between kernel elements. Default: 1

See also

torch.nn.ConvTranspose2d andtorch.nn.modules.lazy.LazyModuleMixin

cls_to_become[source]#

alias ofConvTranspose2d