6biM$SrSSKJs Jr SSKJr SSKJr SSKJr SSKJ r SSKJ r SSK J r SS K Jr SS KJr SS KJr SS KJr SS KJr SSKJr SSKJr \"S5"SS\\ R855r\"S5"SS\55rg)zFully connected RNN layer.N) activations)backend) constraints) initializers) regularizers) base_layer) InputSpec) rnn_utils)RNN)DropoutRNNCellMixin)tf_utils) tf_logging) keras_exportzkeras.layers.SimpleRNNCellc^\rSrSrSrS U4Sjjr\RU4Sj5rS Sjr S Sjr U4Sjr Sr U=r $) SimpleRNNCell%a Cell class for SimpleRNN. See [the TF-Keras RNN API guide](https://www.tensorflow.org/guide/tf_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) ``` c >US::a[SUS35e[RRR 5(aUR SS5UlOUR SS5Ul[TU] "S 0UD6 Xl [R"U5Ul X0l [R"U5Ul[R"U5Ul[R"U5Ul[$R"U5Ul[$R"U5Ul[$R"U 5Ul[,R"U 5Ul[,R"U 5Ul[,R"U 5Ul[5S[7SU 55Ul[5S[7SU55UlURUlURUlg) NrzQReceived an invalid value for argument `units`, expected a positive integer, got .enable_caching_deviceTFg?) 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$r%r&r'r(r)r*r+r,r-r0r1kwargs __class__s \/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/layers/rnn/simple_rnn.pyr SimpleRNNCell.__init__ks$ A:4497!=  99<< ; ; = =*0**'+D '+1**'+D ' "6" %//*5 "."2"23E"F%1%5%56K%L" , 0 01A B"."2"23E"F%1%5%56K%L" , 0 01A B!,1B!C$/OO4H$I!*?3C 12 !$S#c3D*E!F**::c :>[TU]U5 [R"U5nUR USUR 4SUR URURUS9Ul UR UR UR 4SURURURUS9Ul UR(aCUR UR 4SURUR UR"US9UlOSUlSUlg)Nkernel)shapename initializer regularizer constraintcaching_devicerecurrent_kernelbiasT)rbuildr rB add_weightr!r%r(r+r<r&r)r,rCr$r'r*r-rDbuilt)r4 input_shapedefault_caching_devicer6s r7rESimpleRNNCell.builds  k"!*!9!9$!?oor?DJJ/////--1 &  !%::tzz*#2222001 !0!  ==zzm 11 11//5 (DIDI r9cl[RRU5(aUSOUnURX5nUR XC5nUb$[ R "X-UR5nO [ R "XR5nURb [ R"XpR5nUbXF-nU[ R "X@R5-nURbURU5n[RRU5(aU/OUn X4$)Nr) rnest is_nestedget_dropout_mask_for_cell#get_recurrent_dropout_mask_for_cellrdotr<rDbias_addrCr#) r4inputsstatestraining prev_outputdp_mask rec_dp_maskhoutput new_states r7callSimpleRNNCell.calls#%77#4#4V#<#>     F,dkk:A FKK0A 99   II.A  "%3KW[[.C.CDD ?? &__V,F " 1 1& 9 9VHv   r9c0[R"XX#5$N)r #generate_zero_filled_state_for_cell)r4rR batch_sizedtypes r7get_initial_stateSimpleRNNCell.get_initial_states<< *  r9c>UR[R"UR5UR[ R"UR 5[ R"UR5[ R"UR5[R"UR5[R"UR5[R"UR5[R"UR5[R"UR5[R"UR 5UR"UR$S.nUR'[(R*"U55 [,TU]]5n[1[3UR555[3UR555-5$)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_configr6s r7rhSimpleRNNCell.get_configsVZZ%//@ "."8"8''#&2%;%;**&!- 6 6t7L7L M"."8"8''#&2%;%;**&!- 6 6t7L7L M!,!6!6t7M7M!N$/$9$9))% +44T5I5IJ||!%!7!71 4  i@@FGg(* D**,-V\\^0DDEEr9)rr#rDr-r'r*rGr0r<r+r%r(r3r,r1r&rCr)r2r!r$) tanhTglorot_uniform orthogonalzerosNNNNNNrrr^NNN)__name__ __module__ __qualname____firstlineno____doc__r r shape_type_conversionrEr[rbrh__static_attributes__ __classcell__r6s@r7rr%sjBN+* "!4&l##$@!. FFr9rzkeras.layers.SimpleRNNcb^\rSrSrSrSU4SjjrSU4Sjjr\S5r\S5r \S5r \S5r \S 5r \S 5r \S 5r\S 5r\S 5r\S5r\S5r\S5r\S5r\S5rU4Sjr\S5rSrU=r$) SimpleRNNa Fully-connected RNN where the output is to be fed back to input. See [the TF-Keras RNN API guide](https://www.tensorflow.org/guide/tf_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) ``` c >SU;a'URS5 [R"S5 SU;aSURS50nO0n[U40SU_SU_SU_SU_SU_S U_S U_S U _S U _S U _SU _SU_SU_SUR S5_SUR SS5_SS_UD6n[ TU]"U4UUUUUS.UD6 [R"U 5Ul[SS9/Ul g)NimplementationzhThe `implementation` argument in `SimpleRNN` has been deprecated. Please remove it from your layer call.rr#r$r%r&r'r(r)r*r+r,r-r0r1ra trainableTr>simple_rnn_cell)return_sequences return_state go_backwardsstatefulunroll)ndim) rloggingwarningrr"rr ractivity_regularizerr input_spec)r4r!r#r$r%r&r'r(r)r*rr+r,r-r0r1rrrrrr5 cell_kwargscellr6s r7r SimpleRNN.__init__Wsi0 v % JJ' ( OO9  #f ,'4K)LKK  !   2  #8  .   2 #8 . 0 "6 ,  0 **W% jjd3! "#% (   -%%   %1$4$45I$J!$!,-r9c >[TU]XX4S9$)N)maskrT initial_state)rr[)r4rRrrTrr6s r7r[SimpleRNN.callsw|   r9c.URR$r^)rr!r4s r7r!SimpleRNN.unitssyyr9c.URR$r^)rr#rs r7r#SimpleRNN.activationsyy###r9c.URR$r^)rr$rs r7r$SimpleRNN.use_biassyy!!!r9c.URR$r^)rr%rs r7r%SimpleRNN.kernel_initializeryy+++r9c.URR$r^)rr&rs r7r&SimpleRNN.recurrent_initializeryy...r9c.URR$r^)rr'rs r7r'SimpleRNN.bias_initializeryy)))r9c.URR$r^)rr(rs r7r(SimpleRNN.kernel_regularizerrr9c.URR$r^)rr)rs r7r)SimpleRNN.recurrent_regularizerrr9c.URR$r^)rr*rs r7r*SimpleRNN.bias_regularizerrr9c.URR$r^)rr+rs r7r+SimpleRNN.kernel_constraintyy***r9c.URR$r^)rr,rs r7r,SimpleRNN.recurrent_constraintsyy---r9c.URR$r^)rr-rs r7r-SimpleRNN.bias_constraintsyy(((r9c.URR$r^)rr0rs r7r0SimpleRNN.dropoutsyy   r9c.URR$r^)rr1rs r7r1SimpleRNN.recurrent_dropoutrr9c>UR[R"UR5UR[ R"UR 5[ R"UR5[ R"UR5[R"UR5[R"UR5[R"UR5[R"UR5[R"UR5[R"UR 5[R"UR"5UR$UR&S.n[(TU]U5nUR-[.R0"UR255 US [5[7UR955[7UR955-5$)N)r!r#r$r%r&r'r(r)r*rr+r,r-r0r1r)r!rrer#r$rr%r&r'rr(r)r*rrr+r,r-r0r1rrhrfr rgrrirjrkrls r7rhSimpleRNN.get_configs{ZZ%//@ "."8"8''#&2%;%;**&!- 6 6t7L7L M"."8"8''#&2%;%;**&!- 6 6t7L7L M$0$:$:))%"-!6!6t7M7M!N$/$9$9))% +44T5I5IJ||!%!7!77 :g(*  i@@KL  D**,-V\\^0DDEEr9c@SU;aURS5 U"S0UD6$)Nrr)r)clsrms r7 from_configSimpleRNN.from_configs# v % JJ' (}V}r9)rr)rpTrqrrrsNNNNNNNrrFFFFFrt)rurvrwrxryr r[propertyr!r#r$r%r&r'r(r)r*r+r,r-r0r1rh classmethodrr{r|r}s@r7rrsUt+* "!!+C.J $$"",,//**,,//**++..))!!++!FFr9r)rytensorflow.compat.v2rv2r tf_keras.srcrrrrrtf_keras.src.enginertf_keras.src.engine.input_specr tf_keras.src.layers.rnnr tf_keras.src.layers.rnn.base_rnnr .tf_keras.src.layers.rnn.dropout_rnn_cell_mixinr tf_keras.src.utilsr tensorflow.python.platformrr tensorflow.python.util.tf_exportrBaseRandomLayerrrrr9r7rs!"!$ $%%*4-0N'=9*+UF')C)CUF,UFp&'AA(Ar9