&VfDddlmZddlmZddlmZddlmZddlmZddlmZddlmZddl m Z dd l m Z dd l mZdd lmZed Gd de eZedGddeZdS)) activations)backend) constraints) initializers)ops) regularizers) keras_export) InputSpec)Layer)DropoutRNNCell)RNNzkeras.layers.SimpleRNNCellc`eZdZdZ dfd Zd Zdd Zdd ZfdZxZ S) SimpleRNNCellav Cell class for SimpleRNN. This class processes one step within the whole time sequence input, whereas `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 should use 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. seed: Random seed for dropout. Call arguments: sequence: A 2D tensor, with shape `(batch, features)`. states: A 2D tensor with shape `(batch, units)`, which is the state from the previous time step. 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. Example: ```python inputs = np.random.random([32, 10, 8]).astype(np.float32) rnn = keras.layers.RNN(keras.layers.SimpleRNNCell(4)) output = rnn(inputs) # The output has shape `(32, 4)`. rnn = keras.layers.RNN( 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 |dkrtd|dtjdi|||_tj||_||_tj ||_ ||_ tj ||_tj ||_tj ||_t#j ||_t#j ||_t#j | |_t+j | |_t+j | |_t+j | |_t3dt5d| |_t3dt5d||_|j|_|j|_dS)NrzQReceived an invalid value for argument `units`, expected a positive integer, got .g?r) ValueErrorsuper__init__seedrrandom SeedGeneratorseed_generatorunitsrget activationuse_biasrkernel_initializerrecurrent_initializerbias_initializerrkernel_regularizerrecurrent_regularizerbias_regularizerrkernel_constraintrecurrent_constraintbias_constraintminmaxdropoutrecurrent_dropout state_size output_size)selfrr!r"r#r$r%r&r'r(r)r*r+r.r/rkwargs __class__s \/var/www/html/software/conda/lib/python3.11/site-packages/keras/src/layers/rnn/simple_rnn.pyrzSimpleRNNCell.__init__Os& A::=49===  ""6""" %n::4@@ %/*55  "."23E"F"F%1%56K%L%L" , 01A B B"."23E"F"F%1%56K%L%L" , 01A B B!,1B!C!C$/O4H$I$I!*??3C 1 122 !$S#c3D*E*E!F!F*:c||d|jfd|j|j|j|_||j|jfd|j|j|j|_ |j r5||jfd|j |j |j |_nd|_d|_dS)Nkernel)shapename initializer regularizer constraintrecurrent_kernelbiasT) add_weightrr#r&r)r9r$r'r*r?r"r%r(r+r@built)r2 input_shapes r5buildzSimpleRNNCell.buildsoor?DJ///- &   !%:tz*#220 !0! !  = zm 1 1/ (DIIDI r6Fct|ttfr|dn|}||}||}|r|||z}t j||j}|j ||jz }|r|||z}|t j||j z}|j | |}t|ttfr|gn|} || fS)Nr) isinstancelisttupleget_dropout_maskget_recurrent_dropout_maskrmatmulr9r@r?r!) r2sequencestatestraining prev_outputdp_mask rec_dp_maskhoutput new_states r5callzSimpleRNNCell.calls#-ftUm#D#DPfQii& ''1155kBB  *+')H Jx - - 9 NA  4 /% 3KSZ T-BCCC ? &__V,,F *6D%= A AMVHHv y  r6cHtj||jf|jgS)N)dtype)rrr0 compute_dtype)r2 batch_sizes r5get_initial_statezSimpleRNNCell.get_initial_states( Iz4?34;M N N N  r6cr|jtj|j|jt j|jt j|jt j|jtj|j tj|j tj|j tj|jtj|jtj|j|j|j|jd}t)}i||S)N)rr!r"r#r$r%r&r'r(r)r*r+r.r/r)rr serializer!r"rr#r$r%rr&r'r(rr)r*r+r.r/rr get_configr2config base_configr4s r5r]zSimpleRNNCell.get_configsZ%/@@ "."8'##&2%;*&&!- 6t7L M M"."8'##&2%;*&&!- 6t7L M M!,!6t7M!N!N$/$9)%% +4T5IJJ|!%!7I3  6gg((** (+(((r6)rTrrrNNNNNNrrN)FN) __name__ __module__ __qualname____doc__rrDrUrZr] __classcell__r4s@r5rrs==D+* "! !/&/&/&/&/&/&b6!!!!(    )))))))))r6rzkeras.layers.SimpleRNNceZdZdZ dfd Zdfd Zed Zed ZedZ edZ edZ edZ edZ edZedZedZedZedZedZedZfdZedZxZS) SimpleRNNaFully-connected RNN where the output is to be fed back as the new input. 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: sequence: 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. Example: ```python inputs = np.random.random((32, 10, 8)) simple_rnn = keras.layers.SimpleRNN(4) output = simple_rnn(inputs) # The output has shape `(32, 4)`. simple_rnn = 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 @t|fid|d|d|d|d|d|d|d| d | d | d | d |d |d|d|ddd|dddd}tj|f|||||d|t dg|_dS)Nr!r"r#r$r%r&r'r(r)r*r+r.r/rrW trainableTr;simple_rnn_cell)return_sequences return_state go_backwardsstatefulunroll)ndim)rr rrr input_spec)r2rr!r"r#r$r%r&r'r(activity_regularizerr)r*r+r.r/rmrnrorprqrr3cellr4s r5rzSimpleRNN.__init__)sl2    !z X  21  #8"7  .-   21 #8"7 .- 0/ "6!5 ,O G 0/  **Wd+++! "jjd333# $#"% (   -%%      %!,,,-r6cNt||||S)N)maskrN initial_state)rrU)r2 sequencesryrxrNr4s r5rUzSimpleRNN.callas+ww|| D8=   r6c|jjSra)rvrr2s r5rzSimpleRNN.unitsfs yr6c|jjSra)rvr!r|s r5r!zSimpleRNN.activationjs y##r6c|jjSra)rvr"r|s r5r"zSimpleRNN.use_biasns y!!r6c|jjSra)rvr#r|s r5r#zSimpleRNN.kernel_initializerr y++r6c|jjSra)rvr$r|s r5r$zSimpleRNN.recurrent_initializerv y..r6c|jjSra)rvr%r|s r5r%zSimpleRNN.bias_initializerz y))r6c|jjSra)rvr&r|s r5r&zSimpleRNN.kernel_regularizer~rr6c|jjSra)rvr'r|s r5r'zSimpleRNN.recurrent_regularizerrr6c|jjSra)rvr(r|s r5r(zSimpleRNN.bias_regularizerrr6c|jjSra)rvr)r|s r5r)zSimpleRNN.kernel_constraint y**r6c|jjSra)rvr*r|s r5r*zSimpleRNN.recurrent_constraints y--r6c|jjSra)rvr+r|s r5r+zSimpleRNN.bias_constraints y((r6c|jjSra)rvr.r|s r5r.zSimpleRNN.dropouts y  r6c|jjSra)rvr/r|s r5r/zSimpleRNN.recurrent_dropoutrr6c|jtj|j|jt j|jt j|jt j|jtj|j tj|j tj|j tj|j tj|jtj|jtj|j|j|jd}t)}|d=i||S)N)rr!r"r#r$r%r&r'r(rur)r*r+r.r/rv)rrr\r!r"rr#r$r%rr&r'r(rurr)r*r+r.r/rr]r^s r5r]zSimpleRNN.get_configs7Z%/@@ "."8'##&2%;*&&!- 6t7L M M"."8'##&2%;*&&!- 6t7L M M$0$:)%%"-!6t7M!N!N$/$9)%% +4T5IJJ|!%!77  :gg((**  (+(((r6c|di|S)Nrr)clsr_s r5 from_configzSimpleRNN.from_configss}}V}}r6)rTrrrNNNNNNNrrFFFFFN)NNF)rbrcrdrerrUpropertyrr!r"r#r$r%r&r'r(r)r*r+r.r/r] classmethodrrfrgs@r5ririsVQQl+* "!! -6.6.6.6.6.6.p      X$$X$""X",,X,//X/**X*,,X,//X/**X*++X+..X.))X)!!X!++X+ ) ) ) ) )D[r6riN) keras.srcrrrrrrkeras.src.api_exportr keras.src.layers.input_specr keras.src.layers.layerr %keras.src.layers.rnn.dropout_rnn_cellr keras.src.layers.rnn.rnnr rrirr6r5rsn!!!!!!!!!!!!""""""""""""------111111((((((@@@@@@((((((*++B)B)B)B)B)E>B)B),+B)J&''mmmmmmm('mmmr6