ConvTranspose

A grouped, dilated transposed convolution over channels-last input.

padding CROPS the output as interleaved (lo, hi) pairs over the spatial axes; output_padding adds extra length on the output's high side per spatial dim (the stride-ambiguity disambiguator).

__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' = False, *, activation: 'Activation | None' = None, dtype: 'DataType' = DataType.Float32, device: 'Device | None' = None) -> 'None'

Declare the layer's slots. Empty stride/padding/output_padding/ dilation mean unit stride, no crop, zero output padding, unit dilation.

extra_repr

extra_repr(self) -> 'str'

One line of per-class detail for :meth:__repr__ (a layer prints its geometry here).

forward

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

Subclasses define the computation here; call the module itself (m(x)), not forward directly.

set_weights

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

Bind the declared slots directly; raises on a shape mismatch.