class

LazyConvTranspose3d

extends_LazyConvMixinConvTranspose3d

LazyConvTranspose3d(out_channels: int, kernel_size: _Size3d, stride: _Size3d = 1, padding: _Size3d = 0, output_padding: _Size3d = 0, groups: int = 1, bias: bool = True, dilation: _Size3d = 1, padding_mode: str = 'zeros', device: DeviceLike = None, dtype: DTypeLike = None)

source edit

A ConvTranspose3d that infers in_channels from the first input.

Lazy version of the 3D transposed convolution. Combines volumetric upsampling with deferred weight allocation, simplifying the construction of 3D generative decoders and medical image synthesis networks where channel dimensions are computed dynamically.

Parameters

out_channelsint

Number of output channels.

kernel_sizeint or tuple[int, int, int]

Size of the 3D convolving kernel.

strideint or tuple[int, int, int]= 1

Stride (upsampling factor). Default: 1.

paddingint or tuple[int, int, int]= 0

dilation * (kernel_size - 1) - padding zero-padding applied on each side of each spatial axis. String padding is not supported. Default: 0.

output_paddingint or tuple[int, int, int]= 0

Additional size added to one side of each spatial output dimension. Default: 0.

groupsint= 1

Number of blocked connections. Default: 1.

biasbool= True

If True, a learnable bias is added after materialization. Default: True.

dilationint or tuple[int, int, int]= 1

Spacing between kernel elements. Default: 1.

padding_modestr= 'zeros'

"zeros", the only mode; another raises ValueError.

deviceDeviceLike= None

Device used when allocating weights. Default: None.

dtypeDTypeLike= None

Data type used when allocating weights. Default: None.

Attributes

weightParameter or None

None before materialization; shape (in_channels, out_channels // groups, K_D, K_H, K_W) afterwards.

biasParameter or None

None before materialization; (out_channels,) if bias=True.

in_channelsint or None

None before the first forward pass.

Notes

Input: $(N, C_{\text{in}}, D, H, W)$ — $C_{\text{in}}$ is inferred automatically. Output: $(N, C_{\text{out}}, D_{\text{out}}, H_{\text{out}}, W_{\text{out}})$ — same formula as ConvTranspose3d.

State-dict loading. A 5-D weight tensor triggers materialization before parameter copying.

Symmetric 3D encoder–decoder. Pair each LazyConv3d with a LazyConvTranspose3d using matching kernel_size, stride, and padding for lossless spatial reconstruction.

Examples

Lazy 3D decoder block:
>>> import lucid
>>> import lucid.nn as nn
>>> up3d = nn.LazyConvTranspose3d(
...     out_channels=32, kernel_size=4, stride=2, padding=1
... )
>>> x = lucid.zeros(2, 64, 4, 8, 8)   # in_channels=64 inferred
>>> y = up3d(x)
>>> y.shape
(2, 32, 8, 16, 16)
Verify materialization:
>>> import lucid
>>> import lucid.nn as nn
>>> lazy = nn.LazyConvTranspose3d(out_channels=16, kernel_size=3, padding=1)
>>> print(lazy.in_channels)
None
>>> _ = lazy(lucid.zeros(1, 8, 4, 4, 4))
>>> print(lazy.in_channels)
8

Used by 1

lucid.nn.modules

Constructors

dunder

init

→None

__init__(out_channels: int, kernel_size: _Size3d, stride: _Size3d = 1, padding: _Size3d = 0, output_padding: _Size3d = 0, groups: int = 1, bias: bool = True, dilation: _Size3d = 1, padding_mode: str = 'zeros', device: DeviceLike = None, dtype: DTypeLike = None)

source edit

Initialise the LazyConvTranspose3d module. See the class docstring for parameter semantics.

Instance methods

forward

→Tensor

forward(x: Tensor, output_size: Sequence[int] | None = None)

source edit

The eager layer's forward; the first call sizes in_channels from x.

LazyConvTranspose3d(out_channels: int, kernel_size: _Size3d, stride: _Size3d = 1, padding: _Size3d = 0, output_padding: _Size3d = 0, groups: int = 1, bias: bool = True, dilation: _Size3d = 1, padding_mode: str = 'zeros', device: DeviceLike = None, dtype: DTypeLike = None)

Lazy 3D decoder block: >>> import lucid >>> import lucid.nn as nn >>> up3d = nn.LazyConvTranspose3d( ... out_channels=32, kernel_size=4, stride=2, padding=1 ... ) >>> x = lucid.zeros(2, 64, 4, 8, 8) # in_channels=64 inferred >>> y = up3d(x) >>> y.shape (2, 32, 8, 16, 16) Verify materialization: >>> import lucid >>> import lucid.nn as nn >>> lazy = nn.LazyConvTranspose3d(out_channels=16, kernel_size=3, padding=1) >>> print(lazy.in_channels) None >>> _ = lazy(lucid.zeros(1, 8, 4, 4, 4)) >>> print(lazy.in_channels) 8

__init__(out_channels: int, kernel_size: _Size3d, stride: _Size3d = 1, padding: _Size3d = 0, output_padding: _Size3d = 0, groups: int = 1, bias: bool = True, dilation: _Size3d = 1, padding_mode: str = 'zeros', device: DeviceLike = None, dtype: DTypeLike = None)