Python 在 Keras 批量训练期间显示每个 epoch 的进度条
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/39124676/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Show progress bar for each epoch during batchwise training in Keras
提问by Anish Shah
When I load the whole dataset in memory and train the network in Keras using following code:
当我在内存中加载整个数据集并使用以下代码在 Keras 中训练网络时：
model.fit(X, y, nb_epoch=40, batch_size=32, validation_split=0.2, verbose=1)
This generates a progress bar per epoch with metrics like ETA, accuracy, loss, etc
这会在每个时期生成一个进度条，其中包含 ETA、准确性、损失等指标
When I train the network in batches, I'm using the following code
当我批量训练网络时，我使用以下代码
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)
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?
这将为每个批次而不是每个时期生成一个进度条。是否可以在批量训练期间为每个 epoch 生成进度条？
回答by Abhijay Ghildyal
1.
1.
model.fit(X, y, nb_epoch=40, batch_size=32, validation_split=0.2, verbose=1)
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."
在对 的上述更改中verbose=2，如文档中所述：“详细：0 表示不记录到标准输出，1 表示进度条记录，” 2 for one log line per epoch。
It'll show your output as:
它会将您的输出显示为：
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.
2.
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:
如果要显示完成 epoch 的进度条，请保留verbose=0（关闭记录到标准输出）并按以下方式实施：
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()
The output will be as follows:
输出如下：
[============================================================] 100%, epoch 10
[================================================ ============] 100%，纪元 10
3.
3.
If you want to show loss after every n batches, you can use:
如果要在每 n 个批次后显示损失，可以使用：
out_batch = NBatchLogger(display=1000)
model.fit([X_train_aux,X_train_main],Y_train,batch_size=128,callbacks=[out_batch])
Though, I haven't ever tried it before. The above example was taken from this keras github issue: Show Loss Every N Batches #2850
虽然，我以前从未尝试过。上面的例子取自这个 keras github 问题：Show Loss Every N Batches #2850
You can also follow a demo of NBatchLoggerhere:
您还可以按照NBatchLogger此处的演示进行操作：
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.
4.
You can also use progbarfor progress, but it'll print progress batchwise
您也可以progbar用于进度，但它会批量打印进度
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)])
回答by casper.dcl
tqdm(version >= 4.41.0) has also just added built-in support for kerasso you could do:
tqdm（版本 >= 4.41.0）还刚刚添加了内置支持，keras因此您可以执行以下操作：
from tqdm.keras import TqdmCallback
...
model.fit(..., verbose=0, callbacks=[TqdmCallback(verbose=2)])
This turns off keras' progress (verbose=0), and uses tqdminstead. For the callback, verbose=2means separate progressbars for epochs and batches. 1means clear batch bars when done. 0means only show epochs (never show batch bars).
这会关闭keras' 进度 ( verbose=0)，并tqdm改为使用。对于回调，verbose=2意味着 epochs 和 batches 的单独进度条。1表示完成后清除批处理条。0表示只显示纪元（从不显示批次条）。
回答by quester
you can set verbose=0 and set callbacks that will update progress at the end of each fitting,
您可以设置 verbose=0 并设置回调，以在每次拟合结束时更新进度，
clf.fit(X, y, nb_epoch=1, batch_size=data.batch_size, verbose=0, callbacks=[some_callback])
https://keras.io/callbacks/#example-model-checkpoints
https://keras.io/callbacks/#example-model-checkpoints
or set callback https://keras.io/callbacks/#remotemonitor
