+ &jwt^RIt^RIHt^RIHt^RIHt!RR]4t!RR]4t !RR ]4t R#) N)Union)ModulecRaa]tRt^ toRtRV3RlV3RllltRtRtRtVt V;t #)Conv1danApplies a 1-dimensional 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. groups (int, optional): The number of groups for the convolution. Default: ``1``. 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_sizestridepaddingdilationgroupsbias)intbool)format __classdict__s"q/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/mlx/nn/layers/convolution.py __annotate__Conv1d.__annotate__"s[     c <\S V`4W,^8wd\RV RV R24h\P!^W,, 4p \ P PV )V W#W,3R7VnV'd\ P!V34Vn WPn W`n W@n WpnR#)rThe number of input channels (-) must be divisible by the number of groups ()lowhighshapeN)super__init__ ValueErrormathsqrtmxrandomuniformweightzerosrrrr r selfr r r r rrrrscale __class__s &&&&&&&&& rr#Conv1d.__init__"s   1 $0 >66II Arrrrrr r*r2rr2r2T __name__ __module__ __qualname____firstlineno____doc__r#r=rE__static_attributes____classdictcell__ __classcell__r/rs@@rrr s$.B rrcRaa]tRt^UtoRtRV3RlV3RllltRtRtRtVt V;t #)Conv2daApplies a 2-dimensional 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. groups (int, optional): The number of groups for the convolution. Default: ``1``. 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[RS[/#rrrtupler)rrs"rrConv2d.__annotate__ns####3:& # c5j! # sEz" #U ####rc <\S V`4W,^8wd\RV RV R24h\RW4V34wr4p\P !^W^,,V^,,, 4p \ PPV )V V.VOW,N5R7Vn V'd\ P!V34Vn WPn W@n W`nWpnR#)rrrrc8\V\4'dW3#T#N isinstancerrCs&r!Conv2d.__init__..s 1c 2 2qf99rrN)r"r#r$mapr%r&r'r(r)r*r+rrr rrr,s &&&&&&&&& rr#Conv2d.__init__ns   1 $0 >66.s:a#5#5qQi<1QO P ii'';+;{;(  ,1DI   rc4VPPR ,VP, RVPP^, RVPPR, RVP RVP RVP RRV9 2 #) r2r3r4:r2Nr5r6r7r9rr:r;r<s&rr=Conv3d._extra_reprs{{  $t{{232dkk6G6G6J5KL;;,,S12)DKK=I||nK ?dN# % rc\P!WPVPVPVP 4pRV9dW P ,pV#r@)r'conv3dr*r rrrrBs&& rrEConv3d.__call__s= IIadkk4<< O T>II Ar)rrrr r*)r2rr2TrJrSs@@rrkrks#.!!> rrk) r%typingrmlx.corecorer'mlx.nn.layers.baserrrUrkrrr}s? %HVHVMVM`CVCr