6bi8SrSSKJs Jr SSKJr SSKJr SSKJr SSKJ r SSKJ r SSK J r SS K Jr SS KJr SS KJr SS KJr \"S S5"SS\55r\rg)zGKeras 2D transposed convolution layer (sometimes called deconvolution).N) activations)backend) constraints) initializers) regularizers)utils) InputSpec)Conv2D) conv_utils) keras_exportzkeras.layers.Conv2DTransposez#keras.layers.Convolution2DTransposec^\rSrSrSr\R S U4Sjj5rSrSr Sr U4Sjr Sr U=r $) Conv2DTranspose"aTTransposed convolution layer (sometimes called Deconvolution). The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of a normal convolution, i.e., from something that has the shape of the output of some convolution to something that has the shape of its input while maintaining a connectivity pattern that is compatible with said convolution. When using this layer as the first layer in a model, provide the keyword argument `input_shape` (tuple of integers or `None`, does not include the sample axis), e.g. `input_shape=(128, 128, 3)` for 128x128 RGB pictures in `data_format="channels_last"`. 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. 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. output_padding: An integer or tuple/list of 2 integers, specifying the amount of padding along the height and width of the output tensor. Can be a single integer to specify the same value for all spatial dimensions. The amount of output padding along a given dimension must be lower than the stride along that same dimension. If set to `None` (default), the output shape is inferred. 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, specifying the dilation rate for all spatial dimensions for dilated convolution. Specifying different dilation rates for different dimensions is not supported. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. 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. kernel_initializer: Initializer for the `kernel` weights matrix (see `keras.initializers`). Defaults to 'glorot_uniform'. bias_initializer: Initializer for the bias vector (see `keras.initializers`). Defaults to 'zeros'. kernel_regularizer: Regularizer function applied to the `kernel` weights 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`). kernel_constraint: Constraint function applied to the 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. If `output_padding` is specified: ``` new_rows = ((rows - 1) * strides[0] + kernel_size[0] - 2 * padding[0] + output_padding[0]) new_cols = ((cols - 1) * strides[1] + kernel_size[1] - 2 * padding[1] + output_padding[1]) ``` Returns: A tensor of rank 4 representing `activation(conv2dtranspose(inputs, kernel) + bias)`. Raises: ValueError: if `padding` is "causal". ValueError: when both `strides` > 1 and `dilation_rate` > 1. References: - [A guide to convolution arithmetic for deep learning](https://arxiv.org/abs/1603.07285v1) - [Deconvolutional Networks](https://www.matthewzeiler.com/mattzeiler/deconvolutionalnetworks.pdf) c >[TU]"S UUUUUU[R"U5U [R"U 5[R"U 5[ R"U 5[ R"U 5[ R"U5[ R"U5[ R"U5S.UD6 XPlURb}[R"URSSSS9Ul[URUR5H2unnUU:dM[SURSURS35e gg) N)filters kernel_sizestridespadding data_format dilation_rate activationuse_biaskernel_initializerbias_initializerkernel_regularizerbias_regularizeractivity_regularizerkernel_constraintbias_constraintoutput_paddingT) allow_zeroz>Strides must be greater than output padding. Received strides=z, output_padding=.) super__init__rgetrrrr!r normalize_tuplezipr ValueError)selfrrrrr!rrrrrrrrrrrkwargsstrideout_pad __class__s l/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/layers/convolutional/conv2d_transpose.pyr&Conv2DTranspose.__init__s@*  ##'"z2+//0BC)--.>?+//0BC)--.>?!-!1!12F!G)oo.?@'OOO< ! &-    *","<"<##Q(8T#D $'t||T5H5H#If$$,,0LL>:**.*=*=)>aA$J +c [R"U5n[U5S:wa[SUS35eUR 5nUR UR c[SUSUS35e[X5n[SX#0S9Ul URURU4-nURSUURURURS UR S 9UlUR$(aNURS UR4UR&UR(UR*S UR S 9UlOSUlS Ulg) Nz0Inputs should have rank 4. Received input_shape=r#zhThe channel dimension of the inputs to `Conv2DTranspose` should be defined. The input_shape received is z , where axis z> (0-based) is the channel dimension, which found to be `None`.)ndimaxeskernelT)nameshape initializer regularizer constraint trainabledtypebias)tf TensorShapelenr*_get_channel_axisdimsvalueintr input_specrr add_weightrrrr>r7rrrrr?built)r+ input_shape channel_axis input_dim kernel_shapes r0buildConv2DTranspose.buildsgnn[1 { q ((3}A7 --/   L ) / / 7//:m<*^,FF  12 #,1JK''4<<*CC oo////--**&   ==||o 11 11//jj(DIDI r2c [R"U5nUSnURS:XaSupEOSupESupgURRb"URR 5nXnXnUbUOX$nUbUOX%nUR upUR upURcS=pOURup[R"UU URU U URSS9n[R"UU URUU URSS9nURS:XaX0RUU4nOX?UUR4n[R"U5n[R"UUR UUR URURURS9n[R""5(dGURR(a,UR%UR5nUR'U5 UR((aF[R*R-UUR.[R0"URS S 9S 9nUR2bUR3U5$U$) Nrchannels_first)r )r )NNrr!r-dilationrS)rrrrr4)r5)r)r@r9rrankas_listrrr!r deconv_output_lengthrrrstackrconv2d_transposer7executing_eagerlycompute_output_shape set_shapernnbias_addr?convert_data_formatr)r+inputs inputs_shape batch_sizeh_axisw_axisheightwidthrDkernel_hkernel_wstride_hstride_w out_pad_h out_pad_w out_height out_width output_shapeoutput_shape_tensoroutputs out_shapes r0callConv2DTranspose.callsPxx' !!_   / /!NFF!NF #  <<   (<<'')D\FLE!-<3G* 0D!--!\\    &$( (I #'#6#6 I 44  LL$''*  33  LL$''*     / /& j)LL&It||LL hh|4**  KK LLLL((,, ##%%&,,*;*;11&,,?I   i ( ==eenn &::$$1%G ?? &??7+ +r2c $[R"U5R5n[U5nURS:XaSup4nOSup4nUR upgUR upURcS=pOURupURX#'[R"X$UURU UURSS9X$'[R"X%UURU U URSS9X%'[R"U5$)NrQ)rSr rR)rRrSr rrTrS) r@rArWlistrrrr!rr rXrr) r+rJrpc_axisrdrerhrirjrkrlrms r0r\$Conv2DTranspose.compute_output_shapeDsnn[199; K(   / /%, "FF%, "FF!--!\\    &$( (I #'#6#6 I#|| )>>  LL$''*   *>>  LL$''*  ~~l++r2cB>[TU]5nURUS'U$)Nr!)r% get_configr!)r+configr/s r0r{Conv2DTranspose.get_configgs&#%#'#6#6  r2)r?rIrGr7r!)rSrSvalidNNr~NTglorot_uniformzerosNNNNN)__name__ __module__ __qualname____firstlineno____doc__rallow_initializer_layoutr&rNrtr\r{__static_attributes__ __classcell__)r/s@r0rr"snm^ ## + !#2$2h)VM^!,Fr2r)rtensorflow.compat.v2compatv2r@ tf_keras.srcrrrrrtf_keras.src.dtensorrtf_keras.src.engine.input_specr (tf_keras.src.layers.convolutional.conv2dr tf_keras.src.utilsr tensorflow.python.util.tf_exportr rConvolution2DTransposer$r2r0rseN"!$ $%%&4;):"$IEfEET )r2