Keras 中的训练准确率是如何确定每个 epoch 的? [英] How is the training accuracy in Keras determined for every epoch?

问题描述

我正在 Keras 中训练一个模型，如下所示:

I am training a model in Keras with as follows:

model.fit(Xtrn, ytrn batch_size=16, epochs=50, verbose=1, shuffle=True,
          callbacks=[model_checkpoint], validation_data=(Xval, yval))

拟合输出如下所示:

如 model.fit 所示，我的批次大小为 16，总共有 8000 个训练样本，如输出所示.因此，根据我的理解，每 16 个批次都会进行训练.这也意味着训练在单个时期内运行 500 次(即，8000/16 =500)

As shown in the model.fit I have a batch size of 16 and a total of 8000 training samples as shown in the output. So from my understanding, training takes place every 16 batches. Which also means training is ran 500 times for a single epoch (i.e., 8000/16 =500)

因此，让我们采用 Epoch 1/50 输出中打印的训练准确度，在本例中为 0.9381.我想知道 0.9381 的训练精度是如何得出的.

So let's take the training accuracy printed in the output for Epoch 1/50, which in this case is 0.9381. I would like to know how is this training accuracy of 0.9381 derived.

是吗:

1. mean 训练准确率是 500 次训练的平均值吗?

1. Is the mean training accuracy, taken as the average from the 500 times training, performed for every batch?

或，

1. 在运行训练过程的 500 个实例中，它是最佳(或 最大)训练准确度吗?

1. Is it the best (or max) training accuracy from out of the 500 instances the training procedure is run?

推荐答案

看看 Keras 中的 BaseLogger，他们在那里计算运行平均值.对于每个 epoch，准确率是该 epoch 中之前看到的所有批次的平均值.

Take a look at the BaseLogger in Keras where they're computing a running mean. For each epoch the accuracy is the average of all the batches seen before in that epoch.

class BaseLogger(Callback):
    """Callback that accumulates epoch averages of metrics.

    This callback is automatically applied to every Keras model.
    """

    def on_epoch_begin(self, epoch, logs=None):
        self.seen = 0
        self.totals = {}

    def on_batch_end(self, batch, logs=None):
        logs = logs or {}
        batch_size = logs.get('size', 0)
        self.seen += batch_size

        for k, v in logs.items():
            if k in self.totals:
                self.totals[k] += v * batch_size
            else:
                self.totals[k] = v * batch_size

    def on_epoch_end(self, epoch, logs=None):
        if logs is not None:
            for k in self.params['metrics']:
                if k in self.totals:
                    # Make value available to next callbacks.
                    logs[k] = self.totals[k] / self.seen

这篇关于Keras 中的训练准确率是如何确定每个 epoch 的?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！