o ·2úhÉã@sVddlmZddlmZddlmZedgƒGdd„dejƒƒZej dej ¡e_dS) é)Ú keras_export)Úadam)Ú optimizerzkeras.optimizers.AdamWcs@eZdZdZ              d ‡fd d „ Z‡ZS)ÚAdamWa‚Optimizer that implements the AdamW algorithm. AdamW optimization is a stochastic gradient descent method that is based on adaptive estimation of first-order and second-order moments with an added method to decay weights per the techniques discussed in the paper, 'Decoupled Weight Decay Regularization' by [Loshchilov, Hutter et al., 2019](https://arxiv.org/abs/1711.05101). According to [Kingma et al., 2014](http://arxiv.org/abs/1412.6980), the underlying Adam method is "*computationally efficient, has little memory requirement, invariant to diagonal rescaling of gradients, and is well suited for problems that are large in terms of data/parameters*". Args: learning_rate: A float, a `keras.optimizers.schedules.LearningRateSchedule` instance, or a callable that takes no arguments and returns the actual value to use. The learning rate. Defaults to `0.001`. beta_1: A float value or a constant float tensor, or a callable that takes no arguments and returns the actual value to use. The exponential decay rate for the 1st moment estimates. Defaults to `0.9`. beta_2: A float value or a constant float tensor, or a callable that takes no arguments and returns the actual value to use. The exponential decay rate for the 2nd moment estimates. Defaults to `0.999`. epsilon: A small constant for numerical stability. This epsilon is "epsilon hat" in the Kingma and Ba paper (in the formula just before Section 2.1), not the epsilon in Algorithm 1 of the paper. Defaults to 1e-7. amsgrad: Boolean. Whether to apply AMSGrad variant of this algorithm from the paper "On the Convergence of Adam and beyond". Defaults to `False`. {{base_optimizer_keyword_args}} References: - [Loshchilov et al., 2019](https://arxiv.org/abs/1711.05101) - [Kingma et al., 2014](http://arxiv.org/abs/1412.6980) for `adam` - [Reddi et al., 2018]( https://openreview.net/pdf?id=ryQu7f-RZ) for `amsgrad`. çü©ñÒMbP?çü©ñÒMbp?çÍÌÌÌÌÌì?ç+‡ÙÎ÷ï?çH¯¼šò×z>FNç®Gáz®ï?Úadamwc sHtƒjd|||||||||| | | | | |dœ|¤Ž|jdur"tdƒ‚dS)N)Ú learning_rateÚbeta_1Úbeta_2ÚepsilonÚamsgradÚnameÚ weight_decayÚclipnormÚ clipvalueÚglobal_clipnormÚuse_emaÚ ema_momentumÚema_overwrite_frequencyÚloss_scale_factorÚgradient_accumulation_stepszDArgument `weight_decay` must be a float. Received: weight_decay=None©)ÚsuperÚ__init__rÚ ValueError)Úselfr rrrrrrrrrrrrrrÚkwargs©Ú __class__rúU/var/www/html/chatgem/venv/lib/python3.10/site-packages/keras/src/optimizers/adamw.pyr5s0ñð ÿÿzAdamW.__init__)rrrr r FNNNFr NNNr )Ú__name__Ú __module__Ú __qualname__Ú__doc__rÚ __classcell__rrr"r$rs$/ðrz{{base_optimizer_keyword_args}}N) Úkeras.src.api_exportrÚkeras.src.optimizersrrÚAdamrr(ÚreplaceÚbase_optimizer_keyword_argsrrrr$Ús  [ ÿ