BVhd :dZddlZddlmZddlmZddlmZGddejejZ dd d ddd dejdddddd ddfd Z Gd dejejZ dd d ddd dejdddddd ddfdZGddejejZdd d ddd dejdddddd ddfdZGddej"ejZGddej$ejZdd d dddd ddejdddddddd ddfdZdd d dddd ddejdddddddd ddfdZGddej*ejZdd d dd dejdddddd ddfdZGddej.ejZdd d dd dejdddddd ddfd Ze Ze ZeZeZexZxZZexZ xZ!Z"e Z#eZ$eZ%eZ&exZ'xZ(Z)exZ*xZ+Z,y)!zFContains the convolutional layer classes and their functional aliases.N)layers)base)init_opsc`eZdZdZdddddddej dddddddffd ZxZS)Conv1Da 1D convolution layer (e.g. temporal convolution). This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. If `use_bias` is True (and a `bias_initializer` is provided), a bias vector is created and added to the outputs. Finally, if `activation` is not `None`, it is applied to the outputs as well. Args: filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: An integer or tuple/list of a single integer, specifying the length of the 1D convolution window. strides: An integer or tuple/list of a single integer, specifying the stride length of the convolution. 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 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, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. dilation_rate: An integer or tuple/list of a single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any `strides` value != 1. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. valid channels_lastNTc tt| did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d||yNfilters kernel_sizestridespadding data_format dilation_rate activationuse_biaskernel_initializerbias_initializerkernel_regularizerbias_regularizeractivity_regularizerkernel_constraintbias_constraint trainablename)superr__init__selfr rrrrrrrrrrrrrrrrkwargs __class__s f/home/dcms/DCMS/lib/python3.12/site-packages/tensorflow/python/keras/legacy_tf_layers/convolutional.pyr zConv1D.__init__M$ &$     $ .*.*2,( !"V#__name__ __module__ __qualname____doc__rzeros_initializerr __classcell__r$s@r%rrsM2l*"& : : : <"& $$(!%#!##r'rrr r Tctjdtdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|d|}|j|S)a} Functional interface for 1D convolution layer (e.g. temporal convolution). This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. If `use_bias` is True (and a `bias_initializer` is provided), a bias vector is created and added to the outputs. Finally, if `activation` is not `None`, it is applied to the outputs as well. Args: inputs: Tensor input. filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: An integer or tuple/list of a single integer, specifying the length of the 1D convolution window. strides: An integer or tuple/list of a single integer, specifying the stride length of the convolution. 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 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, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. dilation_rate: An integer or tuple/list of a single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any `strides` value != 1. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. reuse: Boolean, whether to reuse the weights of a previous layer by the same name. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. zv`tf.layers.conv1d` is deprecated and will be removed in a future version. Please Use `tf.keras.layers.Conv1D` instead.r rrrrrrrrrrrrrrrr_reuse_scoper)warningswarnrapplyinputsr rrrrrrrrrrrrrrrrreuselayers r%conv1dr:ss^ --?@           "    , ( , ( 0 * &  ! " # $% &' %( V r'c`eZdZdZdddddddej dddddddffd ZxZS)Conv2Da 2D convolution layer (e.g. spatial convolution over images). This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. If `use_bias` is True (and a `bias_initializer` is provided), a bias vector is created and added to the outputs. Finally, if `activation` is not `None`, it is applied to the outputs as well. Args: filters: Integer, the dimensionality of the output space (i.e. the number of 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 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, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. dilation_rate: An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. rrr r NTc tt| did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d||yr )rr<r r!s r%r zConv2D.__init__r&r'r(r/s@r%r<r<sM9z*#"& : : : <"& $$(!%#!##r'r<r=ctjdtdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|d|}|j|S)a Functional interface for the 2D convolution layer. This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. If `use_bias` is True (and a `bias_initializer` is provided), a bias vector is created and added to the outputs. Finally, if `activation` is not `None`, it is applied to the outputs as well. Args: inputs: Tensor input. filters: Integer, the dimensionality of the output space (i.e. the number of 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 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, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. dilation_rate: An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. reuse: Boolean, whether to reuse the weights of a previous layer by the same name. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. zv`tf.layers.conv2d` is deprecated and will be removed in a future version. Please Use `tf.keras.layers.Conv2D` instead.r rrrrrrrrrrrrrrrrr1r2r)r3r4r<r5r6s r%conv2dr@>sl --?@           "    , ( , ( 0 * &  ! " # $% &' %( V r'c`eZdZdZdddddddej dddddddffd ZxZS)Conv3Da 3D convolution layer (e.g. spatial convolution over volumes). This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. If `use_bias` is True (and a `bias_initializer` is provided), a bias vector is created and added to the outputs. Finally, if `activation` is not `None`, it is applied to the outputs as well. Args: filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: An integer or tuple/list of 3 integers, specifying the depth, height and width of the 3D convolution window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the convolution along the depth, 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 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, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. dilation_rate: An integer or tuple/list of 3 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. rrrr r NTc tt| did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d||yr )rrBr r!s r%r zConv3D.__init__r&r'r(r/s@r%rBrBsM:|!*&"& : : : <"& $$(!%#!##r'rBrCctjdtdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|d|}|j|S)a Functional interface for the 3D convolution layer. This layer creates a convolution kernel that is convolved (actually cross-correlated) with the layer input to produce a tensor of outputs. If `use_bias` is True (and a `bias_initializer` is provided), a bias vector is created and added to the outputs. Finally, if `activation` is not `None`, it is applied to the outputs as well. Args: inputs: Tensor input. filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: An integer or tuple/list of 3 integers, specifying the depth, height and width of the 3D convolution window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the convolution along the depth, 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 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, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. dilation_rate: An integer or tuple/list of 3 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. reuse: Boolean, whether to reuse the weights of a previous layer by the same name. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. zv`tf.layers.conv3d` is deprecated and will be removed in a future version. Please Use `tf.keras.layers.Conv3D` instead.r rrrrrrrrrrrrrrrrr1r2r)r3r4rBr5r6s r%conv3drFsn --?@           "    , ( , ( 0 * &  ! " # $% &' %( V r'cheZdZdZdddddddddej dddddddddffd ZxZS)SeparableConv1DaL Depthwise separable 1D convolution. This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If `use_bias` is True and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output. Args: filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: A single integer specifying the spatial dimensions of the filters. strides: A single integer specifying the strides of the convolution. 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 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, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. dilation_rate: A single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. 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 `num_filters_in * depth_multiplier`. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. depthwise_initializer: An initializer for the depthwise convolution kernel. pointwise_initializer: An initializer for the pointwise convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. depthwise_regularizer: Optional regularizer for the depthwise convolution kernel. pointwise_regularizer: Optional regularizer for the pointwise convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. depthwise_constraint: Optional projection function to be applied to the depthwise kernel after being updated by an `Optimizer` (e.g. used for norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. pointwise_constraint: Optional projection function to be applied to the pointwise kernel after being updated by an `Optimizer`. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. rr r NTc tt| did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d|d|d|d|d||yNr rrrrrdepth_multiplierrrdepthwise_initializerpointwise_initializerrdepthwise_regularizerpointwise_regularizerrrdepthwise_constraintpointwise_constraintrrrr)rrHr r"r rrrrrrKrrrLrMrrNrOrrrPrQrrrr#r$s r%r zSeparableConv1D.__init__, /4)    $ *44*44* 2!"2#$2%&('()* -r'r(r/s@r%rHrHsY;~* !%)%) : : : <%)%) $$($($(#),,r'rHcheZdZdZdddddddddej dddddddddffd ZxZS) SeparableConv2DaDepthwise separable 2D convolution. This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If `use_bias` is True and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output. Args: filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: A tuple or list of 2 integers specifying the spatial dimensions of the filters. Can be a single integer to specify the same value for all spatial dimensions. strides: A tuple or list of 2 positive integers specifying the strides of the convolution. 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 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, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. dilation_rate: An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. 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 `num_filters_in * depth_multiplier`. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. depthwise_initializer: An initializer for the depthwise convolution kernel. pointwise_initializer: An initializer for the pointwise convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. depthwise_regularizer: Optional regularizer for the depthwise convolution kernel. pointwise_regularizer: Optional regularizer for the pointwise convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. depthwise_constraint: Optional projection function to be applied to the depthwise kernel after being updated by an `Optimizer` (e.g. used for norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. pointwise_constraint: Optional projection function to be applied to the pointwise kernel after being updated by an `Optimizer`. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. r=r r rNTc tt| did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d|d|d|d|d||yrJ)rrUr rRs r%r zSeparableConv2D.__init__2rSr'r(r/s@r%rUrUsZ@H*# !%)%) : : : <%)%) $$($($(#),,r'rUctjdtdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|d|d|d|d|d|}|j|S)a?Functional interface for the depthwise separable 1D convolution layer. This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If `use_bias` is True and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output. Args: inputs: Input tensor. filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: A single integer specifying the spatial dimensions of the filters. strides: A single integer specifying the strides of the convolution. 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 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, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. dilation_rate: A single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. 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 `num_filters_in * depth_multiplier`. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. depthwise_initializer: An initializer for the depthwise convolution kernel. pointwise_initializer: An initializer for the pointwise convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. depthwise_regularizer: Optional regularizer for the depthwise convolution kernel. pointwise_regularizer: Optional regularizer for the pointwise convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. depthwise_constraint: Optional projection function to be applied to the depthwise kernel after being updated by an `Optimizer` (e.g. used for norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. pointwise_constraint: Optional projection function to be applied to the pointwise kernel after being updated by an `Optimizer`. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. reuse: Boolean, whether to reuse the weights of a previous layer by the same name. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. z`tf.layers.separable_conv1d` is deprecated and will be removed in a future version. Please Use `tf.keras.layers.SeparableConv1D` instead.r rrrrrrKrrrLrMrrNrOrrrPrQrrrr1r2r)r3r4rHr5r7r rrrrrrKrrrLrMrrNrOrrrPrQrrrr8r9s r%separable_conv1drYasx --HI           "  (   2 2 ( 2 2 (  0! "0# $0% &&' () * + ,- ./ %0 V r'ctjdtdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|d|d|d|d|d|}|j|S)aFunctional interface for the depthwise separable 2D convolution layer. This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If `use_bias` is True and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output. Args: inputs: Input tensor. filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: A tuple or list of 2 integers specifying the spatial dimensions of the filters. Can be a single integer to specify the same value for all spatial dimensions. strides: A tuple or list of 2 positive integers specifying the strides of the convolution. 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 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, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. dilation_rate: An integer or tuple/list of 2 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any stride value != 1. 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 `num_filters_in * depth_multiplier`. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. depthwise_initializer: An initializer for the depthwise convolution kernel. pointwise_initializer: An initializer for the pointwise convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. depthwise_regularizer: Optional regularizer for the depthwise convolution kernel. pointwise_regularizer: Optional regularizer for the pointwise convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. depthwise_constraint: Optional projection function to be applied to the depthwise kernel after being updated by an `Optimizer` (e.g. used for norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. pointwise_constraint: Optional projection function to be applied to the pointwise kernel after being updated by an `Optimizer`. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. reuse: Boolean, whether to reuse the weights of a previous layer by the same name. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. z`tf.layers.separable_conv2d` is deprecated and will be removed in a future version. Please Use `tf.keras.layers.SeparableConv2D` instead.r rrrrrrKrrrLrMrrNrOrrrPrQrrrr1r2r)r3r4rUr5rXs r%separable_conv2dr[sB --HI           "  (   2 2 ( 2 2 (  0! "0# $0% &&' () * + ,- ./ %0 V r'c^eZdZdZddddddej dddddddffd ZxZS)Conv2DTransposea Transposed 2D convolution layer (sometimes called 2D 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. Args: filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: A tuple or list of 2 positive integers specifying the spatial dimensions of the filters. Can be a single integer to specify the same value for all spatial dimensions. strides: A tuple or list of 2 positive integers specifying the strides of the convolution. Can be a single integer to specify the same value for all spatial dimensions. padding: one of `"valid"` or `"same"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding 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, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. r=r r NTc tt| did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d||yNr rrrrrrrrrrrrrrrr)rr]r r"r rrrrrrrrrrrrrrrr#r$s r%r zConv2DTranspose.__init__s" /4)     .*.*2,(  #r'r(r/s@r%r]r]ZsJ/f*"& : : : <"& $$(!%#""r'r]ctjdtdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|}|j|S)a Functional interface for transposed 2D convolution layer. 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. Args: inputs: Input tensor. filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: A tuple or list of 2 positive integers specifying the spatial dimensions of the filters. Can be a single integer to specify the same value for all spatial dimensions. strides: A tuple or list of 2 positive integers specifying the strides of the convolution. Can be a single integer to specify the same value for all spatial dimensions. padding: one of `"valid"` or `"same"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding 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, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. activation: Activation function. Set it to `None` to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If `None`, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. reuse: Boolean, whether to reuse the weights of a previous layer by the same name. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. z`tf.layers.conv2d_transpose` is deprecated and will be removed in a future version. Please Use `tf.keras.layers.Conv2DTranspose` instead.r rrrrrrrrrrrrrrrr1r2r)r3r4r]r5r7r rrrrrrrrrrrrrrrr8r9s r%conv2d_transposercsV --HI              , ( , ( 0 * &   ! "# $% %& V r'c^eZdZdZddddddej dddddddffd ZxZS)Conv3DTransposea Transposed 3D convolution layer (sometimes called 3D Deconvolution). Args: filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: An integer or tuple/list of 3 integers, specifying the depth, height and width of the 3D convolution window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the convolution along the depth, height and width. Can be a single integer to specify the same value for all spatial dimensions. padding: One of `"valid"` or `"same"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding 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, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. activation: Activation function. Set it to `None` to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If `None`, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. rCr r NTc tt| did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d||yr_)rrer r`s r%r zConv3DTranspose.__init__Cs$ /4)     .*.*2,(  #r'r(r/s@r%reresJ+`!*"& : : : <"& $$(!%#!##r'rectjdtdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|}|j|S)a_ Functional interface for transposed 3D convolution layer. Args: inputs: Input tensor. filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size: A tuple or list of 3 positive integers specifying the spatial dimensions of the filters. Can be a single integer to specify the same value for all spatial dimensions. strides: A tuple or list of 3 positive integers specifying the strides of the convolution. Can be a single integer to specify the same value for all spatial dimensions. padding: one of `"valid"` or `"same"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding 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, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. activation: Activation function. Set it to None to maintain a linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. bias_initializer: An initializer for the bias vector. If None, the default initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Optional regularizer function for the output. kernel_constraint: Optional projection function to be applied to the kernel after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. bias_constraint: Optional projection function to be applied to the bias after being updated by an `Optimizer`. trainable: Boolean, if `True` also add variables to the graph collection `GraphKeys.TRAINABLE_VARIABLES` (see `tf.Variable`). name: A string, the name of the layer. reuse: Boolean, whether to reuse the weights of a previous layer by the same name. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. z`tf.layers.conv3d_transpose` is deprecated and will be removed in a future version. Please Use `tf.keras.layers.Conv3DTranspose` instead.r rrrrrrrrrrrrrrrr1r2r)r3r4rer5rbs r%conv3d_transposerhisJ --HI              , ( , ( 0 * &   ! "# $% %& V r')-r,r3tensorflow.python.kerasr keras_layers(tensorflow.python.keras.legacy_tf_layersrtensorflow.python.opsrrLayerr-r:r<r@rBrFrHrUrYr[r]rcrerh Convolution1D Convolution2D Convolution3DSeparableConvolution2DConvolution2DTransposeDeconvolution2DDeconv2DConvolution3DTransposeDeconvolution3DDeconv3D convolution1d convolution2d convolution3dseparable_convolution2dconvolution2d_transposedeconvolution2ddeconv2dconvolution3d_transposedeconvolution3ddeconv3drr'r%rs. M:9*X\ $**X|&"6H668" $!%fR_\ $**_J&"6H668" $!%m``\ $**`L&""6H668" $!%nbjl22DJJjZol22DJJoj$!0#$&' $"+/+/&@h&@&@&B+/+/&**.*.*.%)#-wz$$!0#)&' $"+/+/&@h&@&@&B+/+/&**.*.*.%)#-|~Tl22DJJTt$$!0 $"(,&@h&@&@&B(,&**.'+%)##aHQl22DJJQn'$!0 $"(,&@h&@&@&B(,&**.'+%)##[@   (6EEE86EEE8   *7GGG/H7GGG/Hr'