在Keras中分批训练期间显示每个时期的进度条 [英] Show progress bar for each epoch during batchwise training in Keras

问题描述

当我将整个数据集加载到内存中并使用以下代码在Keras中训练网络时:

When I load the whole dataset in memory and train the network in Keras using following code:

model.fit(X, y, nb_epoch=40, batch_size=32, validation_split=0.2, verbose=1)

这会在每个时期生成带有ETA，准确性，损失等指标的进度条

This generates a progress bar per epoch with metrics like ETA, accuracy, loss, etc

当我分批训练网络时，我正在使用以下代码

When I train the network in batches, I'm using the following code

for e in range(40):
        for X, y in data.next_batch():
            model.fit(X, y, nb_epoch=1, batch_size=data.batch_size, verbose=1)

这将为每个批次而不是每个时期生成一个进度条.在分批训练期间是否可以为每个时期生成进度条?

This will generate a progress bar for each batch instead of each epoch. Is it possible to generate a progress bar for each epoch during batchwise training?

推荐答案

1.

model.fit(X, y, nb_epoch=40, batch_size=32, validation_split=0.2, verbose=1)

在上述对verbose=2的更改中，如文档中所述:详细:0表示不记录到stdout，1表示进度条记录，2 for one log line per epoch."

In the above change to verbose=2, as it is mentioned in the documentation: "verbose: 0 for no logging to stdout, 1 for progress bar logging, 2 for one log line per epoch."

它将显示您的输出为:

Epoch 1/100
0s - loss: 0.2506 - acc: 0.5750 - val_loss: 0.2501 - val_acc: 0.3750
Epoch 2/100
0s - loss: 0.2487 - acc: 0.6250 - val_loss: 0.2498 - val_acc: 0.6250
Epoch 3/100
0s - loss: 0.2495 - acc: 0.5750 - val_loss: 0.2496 - val_acc: 0.6250
.....
.....

2.

如果您想显示进度条以完成纪元，请保留verbose=0(关闭记录到stdout的日志)并以以下方式实现:

If you want to show a progress bar for completion of epochs, keep verbose=0 (which shuts out logging to stdout) and implement in the following manner:

from time import sleep
import sys

epochs = 10

for e in range(epochs):
    sys.stdout.write('\r')

    for X, y in data.next_batch():
        model.fit(X, y, nb_epoch=1, batch_size=data.batch_size, verbose=0)

    # print loss and accuracy

    # the exact output you're looking for:
    sys.stdout.write("[%-60s] %d%%" % ('='*(60*(e+1)/10), (100*(e+1)/10)))
    sys.stdout.flush()
    sys.stdout.write(", epoch %d"% (e+1))
    sys.stdout.flush()

输出如下:

[============================================== =============] 100％，时代10

[============================================================] 100%, epoch 10

3.

如果要每n个批次显示一次损失，可以使用:

If you want to show loss after every n batches, you can use:

out_batch = NBatchLogger(display=1000)
model.fit([X_train_aux,X_train_main],Y_train,batch_size=128,callbacks=[out_batch])

不过，我以前从未尝试过.上面的示例摘自该keras github问题:每N批显示损失#2850

Though, I haven't ever tried it before. The above example was taken from this keras github issue: Show Loss Every N Batches #2850

您还可以在此处关注NBatchLogger的演示:

You can also follow a demo of NBatchLogger here:

class NBatchLogger(Callback):
    def __init__(self, display):
        self.seen = 0
        self.display = display

    def on_batch_end(self, batch, logs={}):
        self.seen += logs.get('size', 0)
        if self.seen % self.display == 0:
            metrics_log = ''
            for k in self.params['metrics']:
                if k in logs:
                    val = logs[k]
                    if abs(val) > 1e-3:
                        metrics_log += ' - %s: %.4f' % (k, val)
                    else:
                        metrics_log += ' - %s: %.4e' % (k, val)
            print('{}/{} ... {}'.format(self.seen,
                                        self.params['samples'],
                                        metrics_log))

4.

您也可以使用progbar获取进度，但是它将分批打印进度

You can also use progbar for progress, but it'll print progress batchwise

from keras.utils import generic_utils

progbar = generic_utils.Progbar(X_train.shape[0])

for X_batch, Y_batch in datagen.flow(X_train, Y_train):
    loss, acc = model_test.train([X_batch]*2, Y_batch, accuracy=True)
    progbar.add(X_batch.shape[0], values=[("train loss", loss), ("acc", acc)])

这篇关于在Keras中分批训练期间显示每个时期的进度条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！