a Sic>8@sdZddlmmZddlmZddlmZddlmZddlm Z ddlm Z ddl m Z dd l mZdd lmZdd lmZdd lmZed dGdddeZeZdS)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.Convolution2DTransposecsLeZdZdZejdfdd Zd d Zd d ZddZ fddZ Z S)Conv2DTransposeaTransposed 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)`. It defaults to the `image_data_format` value found in your Keras config file at `~/.keras/keras.json`. If you never set it, then it will be "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) rvalidNTglorot_uniformzerosc stjf||||||t|| t| t| t| t| t|t|t|d|||_|jdurtj |jdddd|_t |j |jD]*\}}||krt d|j d|jdqdS) 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"rrrrrrrrrrr kwargsstrideout_pad __class__g/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/layers/convolutional/conv2d_transpose.pyr&sB  zConv2DTranspose.__init__c Cst|}t|dkr&td|d|}|j|jdurTtd|d|dt||}td||id|_ |j |j |f}|j d||j |j|jd |jd |_|jr|j d |j f|j|j|jd |jd |_nd|_d |_dS) Nz0Inputs should have rank 4. Received input_shape=r$zhThe channel dimension of the inputs to `Conv2DTranspose` should be defined. The input_shape received is z , where axis z> (0-based) is the channel dimension, which found to be `None`.)ndimaxeskernelT)nameshape initializer regularizer constraint trainabledtypebias)tf TensorShapelenr*_get_channel_axisdimsvalueintr input_specrr add_weightrrrr=r6rrrr r>built)r+ input_shape channel_axis input_dim kernel_shaper1r1r2buildsP     zConv2DTranspose.buildc Cst|}|d}|jdkr&d\}}nd\}}d\}}|jjdur\|j}||}||}|durh|n||}|dur||n||}|j\} } |j\} } |jdurd} }n |j\} }tj || |j | | |j dd}tj || |j || |j dd}|jdkr||j ||f}n||||j f}t |}tj||j||j|j |j|j d}tsh||j}|||jrtjj||jtj|jd d d }|jdur||S|S) Nrchannels_first)r!)rr!)NNrr"r-dilationr)rrrrr3)r4)r)r?r8rrankas_listrrr"r deconv_output_lengthrrrstackrconv2d_transposer6executing_eagerlycompute_output_shape set_shapernnbias_addr>convert_data_formatr)r+inputs inputs_shape batch_sizeh_axisw_axisheightwidthrCkernel_hkernel_wstride_hstride_w out_pad_h out_pad_w out_height out_width output_shapeoutput_shape_tensoroutputs out_shaper1r1r2callsx                 zConv2DTranspose.callc Cst|}t|}|jdkr,d\}}}n d\}}}|j\}}|j\}} |jdur^d} } n |j\} } |j||<t j ||||j | ||j dd||<t j ||||j | | |j dd||<t|S)NrN)rr!rO)rOrr!rrPr) r?r@rSlistrrrr"rr rTrr) r+rIrlc_axisr`rardrerfrgrhrir1r1r2rXDs8           z$Conv2DTranspose.compute_output_shapecst}|j|d<|S)Nr")r% get_configr")r+configr/r1r2rsgs  zConv2DTranspose.get_config)r rNNr NTrrNNNNN) __name__ __module__ __qualname____doc__rallow_initializer_layoutr&rMrprXrs __classcell__r1r1r/r2r "s*o4+O#r )rxtensorflow.compat.v2compatv2r?kerasrrrrr keras.dtensorrkeras.engine.input_specr!keras.layers.convolutional.conv2dr keras.utilsr tensorflow.python.util.tf_exportr r Convolution2DTransposer1r1r1r2s$          L