Skip to main content

ConvTranspose

ConvTranspose(in_channels, out_channels, kernel, stride=(), padding=(), output_padding=(), dilation=(), groups=1, bias=True, *, activation=None, dtype=None, device=None)

A grouped, dilated transposed convolution of any rank over channels-last input; kernel fixes the rank.

Args: in_channels: channels of the input. out_channels: channels of the output. kernel: the kernel extents, one per spatial dimension. stride: per-dimension strides; empty means 1. padding: interleaved (low, high) crop pairs, one pair per spatial dimension, removed from the output; empty means no crop. output_padding: extra length added on the high side of each output dimension (the stride ambiguity's tie-breaker); empty means 0. dilation: per-dimension dilations; empty means 1. groups: input-to-output channel groups. bias: declare the bias slot. activation: a fused epilogue applied to every output (a name such as "relu" or an :class:~clika_runtime.Activation value); None for none. dtype: the weight dtype the layer declares; None declares the default dtype (:func:~clika_runtime.get_default_dtype). A load_state_dict casts the checkpoint to the declared dtype; assign=True adopts the checkpoint's own dtype instead. device: where the layer's tensors live; None declares on the cpu.

__init__​

__init__(self, in_channels: 'int', out_channels: 'int', kernel: 'Sequence[int]', stride: 'Sequence[int]' = (), padding: 'Sequence[int]' = (), output_padding: 'Sequence[int]' = (), dilation: 'Sequence[int]' = (), groups: 'int' = 1, bias: 'bool' = True, *, activation: 'ActivationLike' = None, dtype: 'DtypeLike | None' = None, device: 'Device | str | None' = None) -> 'None'

Initialize self. See help(type(self)) for accurate signature.

extra_repr​

extra_repr(self) -> 'str'

extra_repr() -> str

One line of per-class detail for :meth:__repr__; a layer prints its geometry here (in_features=64, out_features=256).

forward​

forward(self, input: 'Tensor') -> 'Tensor'

forward(input) -> Tensor

Channels-last [batch, *spatial, in_channels] to [batch, *spatial', out_channels].

set_weights​

set_weights(self, weight: 'Tensor', bias: 'Tensor | None' = None) -> 'None'

set_weights(weight, bias=None) -> None

Bind the declared slots directly (weight in the [in_channels, *kernel, out_channels // groups] layout); raises RuntimeError on a shape mismatch.