a Sic.@sdZddlmmZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dd lmZdd lmZdd lmZed d GdddeZeZdS)zGKeras 1D transposed convolution layer (sometimes called deconvolution).N) activations) constraints) initializers) regularizers)utils) InputSpec)Conv1D) conv_utils) keras_exportzkeras.layers.Conv1DTransposez#keras.layers.Convolution1DTransposecsLeZdZdZejdfdd Zd d Zd d ZddZ fddZ Z S)Conv1DTransposeaTransposed 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, 3)` for data with 128 time steps and 3 channels. Args: filters: Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution). kernel_size: An integer length of the 1D convolution window. strides: An integer specifying the stride of the convolution along the time dimension. Specifying a stride value != 1 is incompatible with specifying a `dilation_rate` value != 1. Defaults to 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 specifying the amount of padding along the time dimension of the output tensor. The amount of output padding must be lower than the stride. 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, length, channels)` while `channels_first` corresponds to inputs with shape `(batch_size, channels, length)`. dilation_rate: an integer, specifying the dilation rate to use for dilated convolution. Currently, specifying a `dilation_rate` value != 1 is incompatible with specifying a stride value != 1. Also dilation rate larger than 1 is not currently supported. 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: 3D tensor with shape: `(batch_size, steps, channels)` Output shape: 3D tensor with shape: `(batch_size, new_steps, filters)` If `output_padding` is specified: ``` new_timesteps = ((timesteps - 1) * strides + kernel_size - 2 * padding + output_padding) ``` Returns: A tensor of rank 3 representing `activation(conv1dtranspose(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) validNTglorot_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_constraintr output_paddingT) allow_zeroz>Strides must be greater than output padding. Received strides=z, output_padding=.) super__init__rgetrrrrr normalize_tuplezipr ValueError)selfrrrrrrrrrrrrrrrrkwargsstrideout_pad __class__g/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/layers/convolutional/conv1d_transpose.pyr#{sB  zConv1DTranspose.__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 3. Received input_shape=r!zhThe channel dimension of the inputs to `Conv1DTranspose` 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:r3rrrrr;built)r( input_shape channel_axis input_dim kernel_shaper.r.r/buildsP     zConv1DTranspose.buildc Cs*t|}|d}|jdkr"d}nd}||}|jdur>d}n |jd}tj||jd|j||jd|j dd}|jdkr||j |f}n |||j f}tj |jdd} t |} tj j||j| |j|j| |j d} ts||j} | | |jrtj j| |j| d } |jdur&|| S| S) Nrchannels_firstr rrr*dilationr0)r1)rrr dilations)r)r<r5rrr deconv_output_lengthrrrrrconvert_data_formatstacknnconv1d_transposer3upperexecuting_eagerlycompute_output_shape set_shaperbias_addr;r) r(inputs inputs_shape batch_sizet_axislengthr out_length output_shaperoutput_shape_tensoroutputs out_shaper.r.r/callsR            zConv1DTranspose.callcCst|}t|}|jdkr*d\}}nd\}}|jdurBd}n |jd}|j||<tj|||j d|j ||j d|j dd||<t|S)NrK)r rL)rLr rrM) r<r=as_listlistrrrr rPrrrr)r(rFr`c_axisr]rr.r.r/rWs$      z$Conv1DTranspose.compute_output_shapecst}|j|d<|S)Nr)r" get_configr)r(configr,r.r/rh(s  zConv1DTranspose.get_config)r r NNr NTrrNNNNN) __name__ __module__ __qualname____doc__rallow_initializer_layoutr#rJrdrWrh __classcell__r.r.r,r/r !s*V4+6r )rmtensorflow.compat.v2compatv2r<kerasrrrr keras.dtensorrkeras.engine.input_specr!keras.layers.convolutional.conv1dr keras.utilsr tensorflow.python.util.tf_exportr r Convolution1DTransposer.r.r.r/s"