+ &jt^RIt^RIHt^RIHt^RIHt!RR]4t!RR]4t !RR ]4t R#) N)Union)ModulecRaa]tRt^ toRtRV3RlV3RllltRtRtRtVt V;t #)ConvTranspose1daApplies a 1-dimensional transposed convolution over the multi-channel input sequence. The channels are expected to be last i.e. the input shape should be ``NLC`` where: * ``N`` is the batch dimension * ``L`` is the sequence length * ``C`` is the number of input channels Args: in_channels (int): The number of input channels out_channels (int): The number of output channels kernel_size (int): The size of the convolution filters stride (int, optional): The stride when applying the filter. Default: ``1``. padding (int, optional): How many positions to 0-pad the input with. Default: ``0``. dilation (int, optional): The dilation of the convolution. output_padding(int, optional): Additional size added to one side of the output shape. Default: ``0``. bias (bool, optional): If ``True`` add a learnable bias to the output. Default: ``True`` cJ<V^8dQhRS[RS[RS[RS[RS[RS[RS[RS[/#  in_channels out_channels kernel_sizestridepaddingdilationoutput_paddingbias)intbool)format __classdict__s"{/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/mlx/nn/layers/convolution_transpose.py __annotate__ConvTranspose1d.__annotate__"s[---- -  -  ----c 6<\S V`4\P!^W,, 4p \P P V )V W#V3R7VnV'd\P!V34Vn WPn W`n W@n Wpn R#)lowhighshapeN)super__init__mathsqrtmxrandomuniformweightzerosrrrr r selfr r r r rrrrscale __class__s &&&&&&&&& rr!ConvTranspose1d.__init__"s}  !{89:ii''k:(  ,1DI   ,rc,VPPR , RVPP^, RVPP^, RVP RVP RVP RVP RRV9 2#) r, , kernel_size= , stride= , padding= , dilation=, output_padding=, bias=rr'rr rrrr*s&r _extra_reprConvTranspose1d._extra_repr=s{{  $%R (9(9!(<'=>;;,,Q/0 $++G||nK ?"1123dN#  % rc\P!VVPVPVPVP VP 4pRV9dW P,pV#r)r$conv_transpose1dr'r rrrrr*xys&& r__call__ConvTranspose1d.__call__FS    KK KK LL MM      T>II Arrrrrr r'rrrrT __name__ __module__ __qualname____firstlineno____doc__r!r9rA__static_attributes____classdictcell__ __classcell__r,rs@@rrr s#.--6   rrcRaa]tRt^TtoRtRV3RlV3RllltRtRtRtVt V;t #)ConvTranspose2daApplies a 2-dimensional transposed convolution over the multi-channel input image. The channels are expected to be last i.e. the input shape should be ``NHWC`` where: * ``N`` is the batch dimension * ``H`` is the input image height * ``W`` is the input image width * ``C`` is the number of input channels Args: in_channels (int): The number of input channels. out_channels (int): The number of output channels. kernel_size (int or tuple): The size of the convolution filters. stride (int or tuple, optional): The size of the stride when applying the filter. Default: ``1``. padding (int or tuple, optional): How many positions to 0-pad the input with. Default: ``0``. dilation (int or tuple, optional): The dilation of the convolution. output_padding(int or tuple, optional): Additional size added to one side of the output shape. Default: ``0``. bias (bool, optional): If ``True`` add a learnable bias to the output. Default: ``True`` c<V^8dQhRS[RS[RS[S[S[3,RS[S[S[3,RS[S[S[3,RS[S[S[3,RS[S[S[3,RS[/#rrrtupler)rrs"rrConvTranspose2d.__annotate__ms----3:& - c5j! - sEz" -U #-c5j)--rc <\S V`4\RW4WW34wr4rW\P!^W^,,V^,,, 4p \ P PV )V V.VOVN5R7VnV'd\ P!V34Vn WPn W@n W`n WpnR#)c8\V\4'dW3#T#N isinstancerr?s&r*ConvTranspose2d.__init__..{s 1c 2 2qf99rrNr r!mapr"r#r$r%r&r'r(rrr rrr)s &&&&&&&&& rr!ConvTranspose2d.__init__ms 7: 9 ' :8 4 W !{^;k!nLMNii'';+;{;(  ,1DI   ,rc,VPPR , RVPP^, RVPPR, RVP RVP RVP RVP RR V9 2#) rr/r0:rr Nr1r2r3r4r5rr6r7r8s&rr9ConvTranspose2d._extra_repr{{  $%R (9(9!(<'=>;;,,S12)DKK=I||nK ?"1123dN#  % rc\P!VVPVPVPVP VP 4pRV9dW P,pV#r<)r$conv_transpose2dr'r rrrrr>s&& rrAConvTranspose2d.__call__rCrrDrErFrOs@@rrQrQTs#0-->   rrQcRaa]tRt^toRtRV3RlV3RllltRtRtRtVt V;t #)ConvTranspose3da Applies a 3-dimensional transposed convolution over the multi-channel input image. The channels are expected to be last i.e. the input shape should be ``NDHWC`` where: * ``N`` is the batch dimension * ``D`` is the input image depth * ``H`` is the input image height * ``W`` is the input image width * ``C`` is the number of input channels Args: in_channels (int): The number of input channels. out_channels (int): The number of output channels. kernel_size (int or tuple): The size of the convolution filters. stride (int or tuple, optional): The size of the stride when applying the filter. Default: ``1``. padding (int or tuple, optional): How many positions to 0-pad the input with. Default: ``0``. dilation (int or tuple, optional): The dilation of the convolution. output_padding(int or tuple, optional): Additional size added to one side of the output shape. Default: ``0``. bias (bool, optional): If ``True`` add a learnable bias to the output. Default: ``True`` c<V^8dQhRS[RS[RS[S[S[3,RS[S[S[3,RS[S[S[3,RS[S[S[3,RS[S[S[3,RS[/#rrS)rrs"rrConvTranspose3d.__annotate__s----3:& - c5j! - sEz" -U #-c5j)--rc <\S V`4\RW4WW34wr4rW\P!^W^,,V^,,V^,,, 4p \ P PV )V V.VOVN5R7VnV'd\ P!V34Vn WPn W@n W`n WpnR#)c:\V\4'dWV3#T#rXrYr[s&rr\*ConvTranspose3d.__init__..s:a#5#5qQi<1QO P ii'';+;{;(  ,1DI   ,rc,VPPR , RVPP^, RVPPR, RVP RVP RVP RVP RR V9 2#) rr/r0:rNr1r2r3r4r5rr6r7r8s&rr9ConvTranspose3d._extra_reprrcrc\P!VVPVPVPVP VP 4pRV9dW P,pV#r<)r$conv_transpose3dr'r rrrrr>s&& rrAConvTranspose3d.__call__rCrrDrErFrOs@@rrhrhs$2--B   rrh) r"typingrmlx.corecorer$mlx.nn.layers.baserrrQrhrrrzs? %GfGTLfL^OfOr