2Vh)`ddlmZddlmZddlmZddlmZedGddeZy) )backend)ops) keras_export)Layerzkeras.layers.AlphaDropoutcBeZdZdZdfd ZddZdZdZfdZxZ S) AlphaDropoutaApplies Alpha Dropout to the input. Alpha Dropout is a `Dropout` that keeps mean and variance of inputs to their original values, in order to ensure the self-normalizing property even after this dropout. Alpha Dropout fits well to Scaled Exponential Linear Units (SELU) by randomly setting activations to the negative saturation value. Args: rate: Float between 0 and 1. The multiplicative noise will have standard deviation `sqrt(rate / (1 - rate))`. noise_shape: 1D integer tensor representing the shape of the binary alpha dropout mask that will be multiplied with the input. For instance, if your inputs have shape `(batch_size, timesteps, features)` and you want the alpha dropout mask to be the same for all timesteps, you can use `noise_shape=(batch_size, 1, features)`. seed: A Python integer to use as random seed. Call arguments: inputs: Input tensor (of any rank). training: Python boolean indicating whether the layer should behave in training mode (adding alpha dropout) or in inference mode (doing nothing). c t|di|d|cxkrdksntd|||_||_||_|dkDr$t jj||_ d|_ |jy)NrzcInvalid value received for argument `rate`. Expected a float value between 0 and 1. Received: rate=T) super__init__ ValueErrorrateseed noise_shaperrandom SeedGeneratorseed_generatorsupports_masking_build_at_init)selfrrrkwargs __class__s ]/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/layers/regularization/alpha_dropout.pyr zAlphaDropout.__init__#s "6"D~A~""&)    & !8")..">">t"DD  $ c|r|jdkDr|j||j}d}d}| |z}tjtj j ||j|j}tj||j}d|jz d|j|dzzzzdz}| |z|jz} ||z|d|z zz} || z| zS|S)Nrg,x?g2֫?)rr g) r_get_concrete_noise_shaperr greater_equalruniformrcastdtype) rinputstrainingralphascalealpha_pkept_idxabxs rcallzAlphaDropout.call4s  A 88((K6E5EfunG(( "";T5H5H"I Hxx&,,7Hdii-A GQJ(>$>?DHAW tyy(A!Gq8|$<rEs5-()*[)5[)+[)r