【问题标题】：Is it possible to update the learning rate, each batch, based on batch label (y_true) distribution?是否可以根据批次标签（y_true）分布更新每个批次的学习率？
【发布时间】：2020-05-17 22:33:55
【问题描述】：

编辑：请参阅此问题的结尾以获取解决方案

TL;DR：我需要找到一种方法来计算每批的标签分布，并更新学习率。有没有办法访问当前模型的优化器来更新每个批次的 learning_rate？

下面是如何计算标签分布。它可以在损失函数中完成，因为默认情况下，损失是分批计算的。可以在哪里执行还可以访问模型优化器的代码？

def loss(y_true, y_pred):
    y = math_ops.argmax(y_true, axis=1)
    freqs = tf.gather(lf, y)  # equal to lf[y] if `lf` and `y` were numpy array's
    inv_freqs = math_ops.pow(freqs, -1)
    E = 1 / math_ops.reduce_sum(inv_freqs)  # value to use when updating learning rate

解决方案

非常感谢 @mrk 推动我朝着正确的方向解决这个问题！

为了计算每批次的标签分布，然后使用该值来更新优化器的学习率，必须...

创建一个自定义指标，计算每批次的标签分布，并返回频率数组（默认情况下，keras 是按批次优化的，因此每批次都会计算指标）。
通过继承 keras.callbacks.History 类创建一个典型的学习率调度程序
覆盖调度程序的on_batch_end 函数，logs dict 将包含批处理的所有计算指标包括我们的自定义标签分布指标！

创建自定义指标

class LabelDistribution(tf.keras.metrics.Metric):
    """
    Computes the per-batch label distribution (y_true) and stores the array as
    a metric which can be accessed via keras CallBack's

    :param n_class: int - number of distinct output class(es)
    """

    def __init__(self, n_class, name='batch_label_distribution', **kwargs):
        super(LabelDistribution, self).__init__(name=name, **kwargs)
        self.n_class = n_class
        self.label_distribution = self.add_weight(name='ld', initializer='zeros',
                                                  aggregation=VariableAggregation.NONE,
                                                  shape=(self.n_class, ))

    def update_state(self, y_true, y_pred, sample_weight=None):
        y_true = mo.cast(y_true, 'int32')
        y = mo.argmax(y_true, axis=1)
        label_distrib = mo.bincount(mo.cast(y, 'int32'))

        self.label_distribution.assign(mo.cast(label_distrib, 'float32'))

    def result(self):
        return self.label_distribution

    def reset_states(self):
        self.label_distribution.assign([0]*self.n_class)

创建 DRW 学习率调度器

class DRWLearningRateSchedule(keras.callbacks.History):
    """
    Used to implement the Differed Re-weighting strategy from
    [Kaidi Cao, et al. "Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss." (2019)]
    (https://arxiv.org/abs/1906.07413)

    To be included as a metric to model.compile
    `model.compile(..., metrics=[DRWLearningRateSchedule(.01)])`
    """

    def __init__(self, base_lr, ld_metric='batch_label_distribution'):
        super(DRWLearningRateSchedule, self).__init__()

        self.base_lr = base_lr
        self.ld_metric = ld_metric  # name of the LabelDistribution metric

    def on_batch_end(self, batch, logs=None):
        ld = logs.get(self.ld_metric)  # the per-batch label distribution
        current_lr = self.model.optimizer.lr
        # example below of updating the optimizers learning rate
        K.set_value(self.model.optimizer.lr, current_lr * (1 / math_ops.reduce_sum(ld)))

【问题讨论】：

标签： python tensorflow machine-learning math keras

【解决方案1】：

Keras 基于损失的学习率自适应

经过一些研究，我发现this，与其触发衰减，不如为学习率定义另一个函数或值。

from __future__ import absolute_import
from __future__ import print_function

import keras
from keras import backend as K
import numpy as np


class LossLearningRateScheduler(keras.callbacks.History):
    """
    A learning rate scheduler that relies on changes in loss function
    value to dictate whether learning rate is decayed or not.
    LossLearningRateScheduler has the following properties:
    base_lr: the starting learning rate
    lookback_epochs: the number of epochs in the past to compare with the loss function at the current epoch to determine if progress is being made.
    decay_threshold / decay_multiple: if loss function has not improved by a factor of decay_threshold * lookback_epochs, then decay_multiple will be applied to the learning rate.
    spike_epochs: list of the epoch numbers where you want to spike the learning rate.
    spike_multiple: the multiple applied to the current learning rate for a spike.
    """

    def __init__(self, base_lr, lookback_epochs, spike_epochs = None, spike_multiple = 10, decay_threshold = 0.002, decay_multiple = 0.5, loss_type = 'val_loss'):

        super(LossLearningRateScheduler, self).__init__()

        self.base_lr = base_lr
        self.lookback_epochs = lookback_epochs
        self.spike_epochs = spike_epochs
        self.spike_multiple = spike_multiple
        self.decay_threshold = decay_threshold
        self.decay_multiple = decay_multiple
        self.loss_type = loss_type


    def on_epoch_begin(self, epoch, logs=None):

        if len(self.epoch) > self.lookback_epochs:

            current_lr = K.get_value(self.model.optimizer.lr)

            target_loss = self.history[self.loss_type] 

            loss_diff =  target_loss[-int(self.lookback_epochs)] - target_loss[-1]

            if loss_diff <= np.abs(target_loss[-1]) * (self.decay_threshold * self.lookback_epochs):

                print(' '.join(('Changing learning rate from', str(current_lr), 'to', str(current_lr * self.decay_multiple))))
                K.set_value(self.model.optimizer.lr, current_lr * self.decay_multiple)
                current_lr = current_lr * self.decay_multiple

            else:

                print(' '.join(('Learning rate:', str(current_lr))))

            if self.spike_epochs is not None and len(self.epoch) in self.spike_epochs:
                print(' '.join(('Spiking learning rate from', str(current_lr), 'to', str(current_lr * self.spike_multiple))))
                K.set_value(self.model.optimizer.lr, current_lr * self.spike_multiple)

        else:

            print(' '.join(('Setting learning rate to', str(self.base_lr))))
            K.set_value(self.model.optimizer.lr, self.base_lr)


        return K.get_value(self.model.optimizer.lr)




def main():
    return

if __name__ == '__main__':
    main()

【讨论】：

太好了，我以前从未遇到过这种情况。看看我是否可以让它工作并会报告。谢谢！
确认这不足以回答我的问题；但是，它使我朝着正确的方向前进-我相信我已经弄清楚了！将更新（如果可行，将选择您的作为正确答案）
太棒了，我很喜欢你的问题和出色的工作，将我的答案转移到你的特定需求。这就是应该使用 SO 的方式。

更多详情

解决方案

创建自定义指标

创建 DRW 学习率调度器