o i eM@sdZddlmmZddlmZddlmZddlmZddlm Z ddlm Z ddl m Z dd l mZdd lmZdd lmZdd lmZdd lmZddlmZddlmZedGdddee jZedGdddeZdS)zFully connected RNN layer.N) activations)backend) constraints) initializers) regularizers) base_layer) InputSpec) rnn_utils)RNN)DropoutRNNCellMixin)tf_utils) tf_logging) keras_exportzkeras.layers.SimpleRNNCellcsneZdZdZ             dfd d Zejfd d Zdd dZdddZ fddZ Z S) SimpleRNNCella Cell class for SimpleRNN. See [the Keras RNN API guide](https://www.tensorflow.org/guide/keras/rnn) for details about the usage of RNN API. This class processes one step within the whole time sequence input, whereas `tf.keras.layer.SimpleRNN` processes the whole sequence. Args: units: Positive integer, dimensionality of the output space. activation: Activation function to use. Default: hyperbolic tangent (`tanh`). If you pass `None`, no activation is applied (ie. "linear" activation: `a(x) = x`). use_bias: Boolean, (default `True`), whether the layer uses a bias vector. kernel_initializer: Initializer for the `kernel` weights matrix, used for the linear transformation of the inputs. Default: `glorot_uniform`. recurrent_initializer: Initializer for the `recurrent_kernel` weights matrix, used for the linear transformation of the recurrent state. Default: `orthogonal`. bias_initializer: Initializer for the bias vector. Default: `zeros`. kernel_regularizer: Regularizer function applied to the `kernel` weights matrix. Default: `None`. recurrent_regularizer: Regularizer function applied to the `recurrent_kernel` weights matrix. Default: `None`. bias_regularizer: Regularizer function applied to the bias vector. Default: `None`. kernel_constraint: Constraint function applied to the `kernel` weights matrix. Default: `None`. recurrent_constraint: Constraint function applied to the `recurrent_kernel` weights matrix. Default: `None`. bias_constraint: Constraint function applied to the bias vector. Default: `None`. dropout: Float between 0 and 1. Fraction of the units to drop for the linear transformation of the inputs. Default: 0. recurrent_dropout: Float between 0 and 1. Fraction of the units to drop for the linear transformation of the recurrent state. Default: 0. Call arguments: inputs: A 2D tensor, with shape of `[batch, feature]`. states: A 2D tensor with shape of `[batch, units]`, which is the state from the previous time step. For timestep 0, the initial state provided by user will be feed to cell. training: Python boolean indicating whether the layer should behave in training mode or in inference mode. Only relevant when `dropout` or `recurrent_dropout` is used. Examples: ```python inputs = np.random.random([32, 10, 8]).astype(np.float32) rnn = tf.keras.layers.RNN(tf.keras.layers.SimpleRNNCell(4)) output = rnn(inputs) # The output has shape `[32, 4]`. rnn = tf.keras.layers.RNN( tf.keras.layers.SimpleRNNCell(4), return_sequences=True, return_state=True) # whole_sequence_output has shape `[32, 10, 4]`. # final_state has shape `[32, 4]`. whole_sequence_output, final_state = rnn(inputs) ``` tanhTglorot_uniform orthogonalzerosNc s|dkr td|dtjjr|dd|_n|dd|_tjd i|||_ t ||_ ||_ t ||_t ||_t ||_t ||_t ||_t | |_t | |_t | |_t | |_tdtd| |_tdtd||_|j |_|j |_dS) NrzQReceived an invalid value for argument `units`, expected a positive integer, got .enable_caching_deviceTFg?r) ValueErrortfcompatv1#executing_eagerly_outside_functionspop_enable_caching_devicesuper__init__unitsrget activationuse_biasrkernel_initializerrecurrent_initializerbias_initializerrkernel_regularizerrecurrent_regularizerbias_regularizerrkernel_constraintrecurrent_constraintbias_constraintminmaxdropoutrecurrent_dropout state_size output_size)selfr!r#r$r%r&r'r(r)r*r+r,r-r0r1kwargs __class__rN/var/www/myenv/lib/python3.10/site-packages/keras/src/layers/rnn/simple_rnn.pyr js<            zSimpleRNNCell.__init__cst|t|}|j|d|jfd|j|j|j|d|_ |j|j|jfd|j |j |j |d|_ |jrG|j|jfd|j|j|j|d|_nd|_d|_dS)Nkernel)shapename initializer regularizer constraintcaching_devicerecurrent_kernelbiasT)rbuildr r@ add_weightr!r%r(r+r:r&r)r,rAr$r'r*r-rBbuilt)r4 input_shapedefault_caching_devicer6rr8rCs:      zSimpleRNNCell.buildc Cstj|r |dn|}|||}|||}|dur&t|||j}nt||j}|jdur9t ||j}|durA||}|t||j }|j durT| |}tj|r]|gn|} || fS)Nr) rnest is_nestedget_dropout_mask_for_cell#get_recurrent_dropout_mask_for_cellrdotr:rBbias_addrAr#) r4inputsstatestraining prev_outputdp_mask rec_dp_maskhoutput new_staterrr8calls"    zSimpleRNNCell.callcCst||||SN)r #generate_zero_filled_state_for_cell)r4rN batch_sizedtyperrr8get_initial_stateszSimpleRNNCell.get_initial_statecs|jt|j|jt|jt|jt|jt |j t |j t |j t |jt |jt |j|j|jd}|t|t}tt|t|S)N)r!r#r$r%r&r'r(r)r*r+r,r-r0r1)r!r serializer#r$rr%r&r'rr(r)r*rr+r,r-r0r1updater config_for_enable_caching_devicer get_configdictlistitemsr4config base_configr6rr8r`s8      zSimpleRNNCell.get_config) rTrrrNNNNNNrrrXNNN) __name__ __module__ __qualname____doc__r r shape_type_conversionrCrWr\r` __classcell__rrr6r8r%s*F6 rzkeras.layers.SimpleRNNcseZdZdZ               d.fd d Zd/fd d ZeddZeddZeddZ eddZ eddZ eddZ eddZ eddZeddZed d!Zed"d#Zed$d%Zed&d'Zed(d)Zfd*d+Zed,d-ZZS)0 SimpleRNNa6Fully-connected RNN where the output is to be fed back to input. See [the Keras RNN API guide](https://www.tensorflow.org/guide/keras/rnn) for details about the usage of RNN API. Args: units: Positive integer, dimensionality of the output space. activation: Activation function to use. Default: hyperbolic tangent (`tanh`). If you pass None, no activation is applied (ie. "linear" activation: `a(x) = x`). use_bias: Boolean, (default `True`), whether the layer uses a bias vector. kernel_initializer: Initializer for the `kernel` weights matrix, used for the linear transformation of the inputs. Default: `glorot_uniform`. recurrent_initializer: Initializer for the `recurrent_kernel` weights matrix, used for the linear transformation of the recurrent state. Default: `orthogonal`. bias_initializer: Initializer for the bias vector. Default: `zeros`. kernel_regularizer: Regularizer function applied to the `kernel` weights matrix. Default: `None`. recurrent_regularizer: Regularizer function applied to the `recurrent_kernel` weights matrix. Default: `None`. bias_regularizer: Regularizer function applied to the bias vector. Default: `None`. activity_regularizer: Regularizer function applied to the output of the layer (its "activation"). Default: `None`. kernel_constraint: Constraint function applied to the `kernel` weights matrix. Default: `None`. recurrent_constraint: Constraint function applied to the `recurrent_kernel` weights matrix. Default: `None`. bias_constraint: Constraint function applied to the bias vector. Default: `None`. dropout: Float between 0 and 1. Fraction of the units to drop for the linear transformation of the inputs. Default: 0. recurrent_dropout: Float between 0 and 1. Fraction of the units to drop for the linear transformation of the recurrent state. Default: 0. return_sequences: Boolean. Whether to return the last output in the output sequence, or the full sequence. Default: `False`. return_state: Boolean. Whether to return the last state in addition to the output. Default: `False` go_backwards: Boolean (default False). If True, process the input sequence backwards and return the reversed sequence. stateful: Boolean (default False). If True, the last state for each sample at index i in a batch will be used as initial state for the sample of index i in the following batch. unroll: Boolean (default False). If True, the network will be unrolled, else a symbolic loop will be used. Unrolling can speed-up a RNN, although it tends to be more memory-intensive. Unrolling is only suitable for short sequences. Call arguments: inputs: A 3D tensor, with shape `[batch, timesteps, feature]`. mask: Binary tensor of shape `[batch, timesteps]` indicating whether a given timestep should be masked. An individual `True` entry indicates that the corresponding timestep should be utilized, while a `False` entry indicates that the corresponding timestep should be ignored. training: Python boolean indicating whether the layer should behave in training mode or in inference mode. This argument is passed to the cell when calling it. This is only relevant if `dropout` or `recurrent_dropout` is used. initial_state: List of initial state tensors to be passed to the first call of the cell. Examples: ```python inputs = np.random.random([32, 10, 8]).astype(np.float32) simple_rnn = tf.keras.layers.SimpleRNN(4) output = simple_rnn(inputs) # The output has shape `[32, 4]`. simple_rnn = tf.keras.layers.SimpleRNN( 4, return_sequences=True, return_state=True) # whole_sequence_output has shape `[32, 10, 4]`. # final_state has shape `[32, 4]`. whole_sequence_output, final_state = simple_rnn(inputs) ``` rTrrrNrFc sd|vr|dtdd|vrd|di}ni}t|fid|d|d|d|d|d |d |d | d | d | d| d|d|d|dd|dddd|}tj|f|||||d|t| |_t ddg|_ dS)NimplementationzhThe `implementation` argument in `SimpleRNN` has been deprecated. Please remove it from your layer call.rr#r$r%r&r'r(r)r*r+r,r-r0r1r[ trainableTr<simple_rnn_cell)return_sequences return_state go_backwardsstatefulunroll)ndim) rloggingwarningrr"rr ractivity_regularizerr input_spec)r4r!r#r$r%r&r'r(r)r*r{r+r,r-r0r1rrrsrtrurvr5 cell_kwargscellr6rr8r Ust          zSimpleRNN.__init__cstj||||dS)N)maskrP initial_state)rrW)r4rNrrPrr6rr8rWszSimpleRNN.callcC|jjSrX)r~r!r4rrr8r!zSimpleRNN.unitscCrrX)r~r#rrrr8r#rzSimpleRNN.activationcCrrX)r~r$rrrr8r$rzSimpleRNN.use_biascCrrX)r~r%rrrr8r%rzSimpleRNN.kernel_initializercCrrX)r~r&rrrr8r&rzSimpleRNN.recurrent_initializercCrrX)r~r'rrrr8r'rzSimpleRNN.bias_initializercCrrX)r~r(rrrr8r(rzSimpleRNN.kernel_regularizercCrrX)r~r)rrrr8r)rzSimpleRNN.recurrent_regularizercCrrX)r~r*rrrr8r*rzSimpleRNN.bias_regularizercCrrX)r~r+rrrr8r+rzSimpleRNN.kernel_constraintcCrrX)r~r,rrrr8r,rzSimpleRNN.recurrent_constraintcCrrX)r~r-rrrr8r-rzSimpleRNN.bias_constraintcCrrX)r~r0rrrr8r0rzSimpleRNN.dropoutcCrrX)r~r1rrrr8r1rzSimpleRNN.recurrent_dropoutcs|jt|j|jt|jt|jt|jt |j t |j t |j t |j t|jt|jt|j|j|jd}t}|t|j|d=tt|t|S)N)r!r#r$r%r&r'r(r)r*r{r+r,r-r0r1r~)r!rr]r#r$rr%r&r'rr(r)r*r{rr+r,r-r0r1rr`r^r r_r~rarbrcrdr6rr8r`s@      zSimpleRNN.get_configcCs d|vr |d|di|S)Nror)r)clsrerrr8 from_configs zSimpleRNN.from_config)rTrrrNNNNNNNrrFFFFFrg)rhrirjrkr rWpropertyr!r#r$r%r&r'r(r)r*r+r,r-r0r1r` classmethodrrmrrr6r8rnslYE               #rn)rktensorflow.compat.v2rv2r keras.srcrrrrrkeras.src.enginerkeras.src.engine.input_specrkeras.src.layers.rnnr keras.src.layers.rnn.base_rnnr +keras.src.layers.rnn.dropout_rnn_cell_mixinr keras.src.utilsr tensorflow.python.platformr ry tensorflow.python.util.tf_exportrBaseRandomLayerrrnrrrr8s(             X