6bi"SrSSKJs Jr SSKJr SSKJr SSKJr SSKJ r SSK J r SSK J r SS KJr \"S S 5"S S \ 55r\rg)z)Keras depthwise separable 2D convolution.N) activations) constraints) initializers) regularizers) SeparableConv) conv_utils) keras_exportzkeras.layers.SeparableConv2Dz#keras.layers.SeparableConvolution2DcX^\rSrSrSrSU4SjjrSrSrU=r$)SeparableConv2DaDepthwise separable 2D convolution. Separable convolutions consist of first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes the resulting output channels. The `depth_multiplier` argument controls how many output channels are generated per input channel in the depthwise step. Intuitively, separable convolutions can be understood as a way to factorize a convolution kernel into two smaller kernels, or as an extreme version of an Inception block. Args: filters: Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution). kernel_size: An integer or tuple/list of 2 integers, specifying the height and width of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 2 integers, specifying the strides of the convolution along the height and width. Can be a single integer to specify the same value for all spatial dimensions. Current implementation only supports equal length strides in the row and column dimensions. Specifying any stride value != 1 is incompatible with specifying any `dilation_rate` value != 1. padding: one of `"valid"` or `"same"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding with zeros evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. data_format: A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch_size, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch_size, channels, height, width)`. When unspecified, uses `image_data_format` value found in your Keras config file at `~/.keras/keras.json` (if exists) else 'channels_last'. Defaults to 'channels_last'. dilation_rate: An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. depth_multiplier: The number of depthwise convolution output channels for each input channel. The total number of depthwise convolution output channels will be equal to `filters_in * depth_multiplier`. activation: Activation function to use. If you don't specify anything, no activation is applied (see `keras.activations`). use_bias: Boolean, whether the layer uses a bias vector. depthwise_initializer: An initializer for the depthwise convolution kernel (see `keras.initializers`). If None, then the default initializer ('glorot_uniform') will be used. pointwise_initializer: An initializer for the pointwise convolution kernel (see `keras.initializers`). If None, then the default initializer ('glorot_uniform') will be used. bias_initializer: An initializer for the bias vector. If None, the default initializer ('zeros') will be used (see `keras.initializers`). depthwise_regularizer: Regularizer function applied to the depthwise kernel matrix (see `keras.regularizers`). pointwise_regularizer: Regularizer function applied to the pointwise kernel matrix (see `keras.regularizers`). bias_regularizer: Regularizer function applied to the bias vector (see `keras.regularizers`). activity_regularizer: Regularizer function applied to the output of the layer (its "activation") (see `keras.regularizers`). depthwise_constraint: Constraint function applied to the depthwise kernel matrix (see `keras.constraints`). pointwise_constraint: Constraint function applied to the pointwise kernel matrix (see `keras.constraints`). bias_constraint: Constraint function applied to the bias vector (see `keras.constraints`). Input shape: 4D tensor with shape: `(batch_size, channels, rows, cols)` if data_format='channels_first' or 4D tensor with shape: `(batch_size, rows, cols, channels)` if data_format='channels_last'. Output shape: 4D tensor with shape: `(batch_size, filters, new_rows, new_cols)` if data_format='channels_first' or 4D tensor with shape: `(batch_size, new_rows, new_cols, filters)` if data_format='channels_last'. `rows` and `cols` values might have changed due to padding. Returns: A tensor of rank 4 representing `activation(separableconv2d(inputs, kernel) + bias)`. Raises: ValueError: if `padding` is "causal". c V>[TU]"S0SS_SU_SU_SU_SU_SU_SU_S U_S [R"U5_S U _S [R"U 5_S [R"U 5_S[R"U 5_S[ R"U 5_S[ R"U5_S[ R"U5_S[ R"U5_S[ R"U5_S[ R"U5_S[ R"U5_UD6 g)Nrankfilters kernel_sizestridespadding data_format dilation_ratedepth_multiplier activationuse_biasdepthwise_initializerpointwise_initializerbias_initializerdepthwise_regularizerpointwise_regularizerbias_regularizeractivity_regularizerdepthwise_constraintpointwise_constraintbias_constraint)super__init__rgetrrr)selfrrrrrrrrrrrrrrrrr r!r"kwargs __class__s l/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/layers/convolutional/separable_conv2d.pyr%SeparableConv2D.__init__sS.    $     $  ( . #z2  #/"2"23H"I #/"2"23H"I *--.>? #/"2"23H"I #/"2"23H"I *--.>?! "".!1!12F!G# $"-1E!F% &"-1E!F' ((OOO<+ c @URS:XaSUR-S-nOSUR-n[RR UUR UR UURR5UR[R"URSS9S9nUR(aF[RRUUR[R"URSS9S9nURbURU5$U$)N channels_last)r/r/)ndim)rr dilationsr)r)rrtfnnseparable_conv2ddepthwise_kernelpointwise_kernelrupperrrconvert_data_formatrbias_addbiasr)r'inputsroutputss r*callSeparableConv2D.calls    .T\\)D0Gt||+G%%((   ! !  ! !LL&&((("66  q)   ==eenn &::$$1%G ?? &??7+ +r,r#)r0validNr0r/NTglorot_uniformrBzerosNNNNNNN) __name__ __module__ __qualname____firstlineno____doc__r%r?__static_attributes__ __classcell__)r)s@r*r r sObP.. ""!!!)- ^r,r )rHtensorflow.compat.v2compatv2r4 tf_keras.srcrrrr5tf_keras.src.layers.convolutional.base_separable_convrtf_keras.src.utilsr tensorflow.python.util.tf_exportr r SeparableConvolution2Dr#r,r*rSs[0"!$$%%O):"$Iqmqql)r,