如何将 Keras 丢失输出记录到文件中 [英] How to log Keras loss output to a file

问题描述

当您运行 Keras 神经网络模型时，您可能会在控制台中看到如下内容:

When you run a Keras neural network model you might see something like this in the console:

Epoch 1/3
   6/1000 [..............................] - ETA: 7994s - loss: 5111.7661

随着时间的推移，损失有望改善.我想随着时间的推移将这些损失记录到一个文件中，以便我可以从中学习.我试过了:

As time goes on the loss hopefully improves. I want to log these losses to a file over time so that I can learn from them. I have tried:

logging.basicConfig(filename='example.log', filemode='w', level=logging.DEBUG)

但这不起作用.我不确定在这种情况下我需要什么级别的日志记录.

but this doesn't work. I am not sure what level of logging I need in this situation.

我也尝试过使用如下回调:

I have also tried using a callback like in:

def generate_train_batch():
    while 1:
        for i in xrange(0,dset_X.shape[0],3):
            yield dset_X[i:i+3,:,:,:],dset_y[i:i+3,:,:]

class LossHistory(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.losses = []

    def on_batch_end(self, batch, logs={}):
        self.losses.append(logs.get('loss'))
logloss=LossHistory()
colorize.fit_generator(generate_train_batch(),samples_per_epoch=1000,nb_epoch=3,callbacks=['logloss'])

但显然这不是写入文件.无论采用何种方法，通过回调或日志记录模块或其他任何方式，我都希望听到您将 keras 神经网络的丢失记录到文件中的解决方案.谢谢！

but obviously this isn't writing to a file. Whatever the method, through a callback or the logging module or anything else, I would love to hear your solutions for logging loss of a keras neural network to a file. Thanks!

推荐答案

您的问题有一个简单的解决方案.每次使用任何 fit 方法时，都会返回名为 History Callback 的特殊回调.它有一个字段 history，它是每个 epoch 之后注册的所有指标的字典.因此，要在每个时期之后获取损失函数值列表，您可以轻松做到:

There is a simple solution to your problem. Every time any of the fit methods are used - as a result the special callback called History Callback is returned. It has a field history which is a dictionary of all metrics registered after every epoch. So to get list of loss function values after every epoch you can easly do:

history_callback = model.fit(params...)
loss_history = history_callback.history["loss"]

将此类列表保存到文件中很容易(例如，将其转换为 numpy 数组并使用 savetxt 方法).

It's easy to save such list to a file (e.g. by converting it to numpy array and using savetxt method).

更新:

试试:

import numpy
numpy_loss_history = numpy.array(loss_history)
numpy.savetxt("loss_history.txt", numpy_loss_history, delimiter=",")

更新 2:

Keras Callbacks DocumentationKeras Callbacks Documentation 在 创建回调 段落中.

这篇关于如何将 Keras 丢失输出记录到文件中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！