► Keras 3 API 文档 / 优化器 / AdamW, an implementation of Adam optimizer with weight decay.

AdamW, an implementation of Adam optimizer with weight decay.

[source]

AdamW class

keras.optimizers.AdamW(
    learning_rate=0.001,
    weight_decay=0.004,
    beta_1=0.9,
    beta_2=0.999,
    epsilon=1e-07,
    amsgrad=False,
    clipnorm=None,
    clipvalue=None,
    global_clipnorm=None,
    use_ema=False,
    ema_momentum=0.99,
    ema_overwrite_frequency=None,
    loss_scale_factor=None,
    gradient_accumulation_steps=None,
    name="adamw",
    **kwargs
)

实现AdamW算法的优化器.

AdamW优化是一种基于随机梯度下降的方法,它基于对一阶和二阶矩的自适应估计,并添加了一种权重衰减方法,具体讨论见论文《解耦权重衰减正则化》, Loshchilov, Hutter 等, 2019.

根据 Kingma 等, 2014, 基础的Adam方法具有"计算效率高,内存需求小,对梯度的对角缩放不变,并且非常适合数据/参数规模大的问题”.

参数: learning_rate: 一个浮点数,一个 keras.optimizers.schedules.LearningRateSchedule实例,或 一个不接受参数并返回实际值的调用.学习率.默认为0.001. beta_1: 一个浮点值或一个常量浮点张量,或一个 不接受参数并返回实际值的调用.一阶矩估计的指数衰减率. 默认为0.9. beta_2: 一个浮点值或一个常量浮点张量,或一个 不接受参数并返回实际值的调用.二阶矩估计的指数衰减率. 默认为0.999. epsilon: 一个小的常数,用于数值稳定性.这个epsilon是 Kingma和Ba论文中的"epsilon hat”（在公式2.1之前）,不是论文中算法1的epsilon. 默认为1e-7. amsgrad: 布尔值.是否应用AMSGrad变种 来自论文《On the Convergence of Adam and beyond》. 默认为False. name: String. The name to use for momentum accumulator weights created by the optimizer. weight_decay: Float. If set, weight decay is applied. clipnorm: Float. If set, the gradient of each weight is individually clipped so that its norm is no higher than this value. clipvalue: Float. If set, the gradient of each weight is clipped to be no higher than this value. global_clipnorm: Float. If set, the gradient of all weights is clipped so that their global norm is no higher than this value. use_ema: Boolean, defaults to False. If True, exponential moving average (EMA) is applied. EMA consists of computing an exponential moving average of the weights of the model (as the weight values change after each training batch), and periodically overwriting the weights with their moving average. ema_momentum: Float, defaults to 0.99. Only used if use_ema=True. This is the momentum to use when computing the EMA of the model's weights: new_average = ema_momentum * old_average + (1 - ema_momentum) * current_variable_value. ema_overwrite_frequency: Int or None, defaults to None. Only used if use_ema=True. Every ema_overwrite_frequency steps of iterations, we overwrite the model variable by its moving average. If None, the optimizer does not overwrite model variables in the middle of training, and you need to explicitly overwrite the variables at the end of training by calling optimizer.finalize_variable_values() (which updates the model variables in-place). When using the built-in fit() training loop, this happens automatically after the last epoch, and you don't need to do anything. loss_scale_factor: Float or None. If a float, the scale factor will be multiplied the loss before computing gradients, and the inverse of the scale factor will be multiplied by the gradients before updating variables. Useful for preventing underflow during mixed precision training. Alternately, keras.optimizers.LossScaleOptimizer will automatically set a loss scale factor. gradient_accumulation_steps: Int or None. If an int, model & optimizer variables will not be updated at every step; instead they will be updated every gradient_accumulation_steps steps, using the average value of the gradients since the last update. This is known as "gradient accumulation". This can be useful when your batch size is very small, in order to reduce gradient noise at each update step. EMA frequency will look at "accumulated" iterations value (optimizer steps // gradient_accumulation_steps). Learning rate schedules will look at "real" iterations value (optimizer steps).

参考文献:

AdamW, an implementation of Adam optimizer with weight decay.
AdamW class