- class torch.nn.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]¶
torch.nn.ConvTranspose2dmodule with lazy initialization of the
in_channelsargument of the
ConvTranspose2dthat is inferred from the
input.size(1). The attributes that will be lazily initialized are weight and bias.
torch.nn.modules.lazy.LazyModuleMixinfor further documentation on lazy modules and their limitations.
out_channels (int) – Number of channels produced by the convolution
stride (int or tuple, optional) – Stride of the convolution. Default: 1
padding (int or tuple, optional) –
dilation * (kernel_size - 1) - paddingzero-padding will be added to both sides of each dimension in the input. Default: 0
output_padding (int or tuple, optional) – Additional size added to one side of 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) – If
True, adds a learnable bias to the output. Default:
dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1