小编Hen*_*ang的帖子

我正在用 Keras 实现一个简单的 CNN，并尝试在 Adam 中设置逐层学习率。我参考了这个教程。修改后的Adam如下图：

class Adam_lr_mult(Optimizer): 
    def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999,
                 epsilon=None, decay=0., amsgrad=False,
                 multipliers=None, debug_verbose=True,**kwargs):
        ...'''Omitted'''

        self.multipliers = multipliers
        self.layerwise_lr={}    # record layer-wise lr
        self.debug_verbose = debug_verbose

    @interfaces.legacy_get_updates_support
    def get_updates(self, loss, params):
        grads = self.get_gradients(loss, params)
        self.updates = [K.update_add(self.iterations, 1)]

        lr = self.lr
        if self.initial_decay > 0:
        lr *= (1. / (1. + self.decay * K.cast(self.iterations,
                                              K.dtype(self.decay))))

        t = K.cast(self.iterations, K.floatx()) + 1
        lr_t = lr * (K.sqrt(1. - K.pow(self.beta_2, t)) /
                     (1. - K.pow(self.beta_1, …