[英]How to window or reset streaming operations in tensorflow?
Tensorflow provides all sorts of nice streaming operations to aggregate statistics along batches, such as tf.metrics.mean
. Tensorflow提供各种漂亮的流操作来汇总统计信息,例如
tf.metrics.mean
。
However I find that accumulating all values since the beginning often does not make a lot of sense. 但是,我发现从一开始就积累所有值通常没有多大意义。 For example, one could rather want to have statistics per epoch, or any other time window that makes sense in a given context.
例如,一个宁愿希望每个时期或在给定上下文中有意义的任何其他时间窗口都有统计信息。
Is there any way to restrict the history of such streaming statistics, for example by reseting streaming operations so that they start over the accumulation? 是否有任何方法可以限制此类流统计的历史记录,例如通过重置流操作以使它们重新开始累积?
Work-arounds: 解决方法:
One way to do it is to call the initializer of the relevant variables in the streaming op. 一种方法是在流操作中调用相关变量的初始化程序。 For example,
例如,
import tensorflow as tf
x = tf.random_normal(())
mean_x, update_op = tf.metrics.mean(x, name='mean_x')
# get the initializers of the local variables (total and count)
my_metric_variables = [v for v in tf.local_variables() if v.name.startswith('mean_x/')]
# or maybe just
# my_metric_variables = tf.get_collection('metric_variables')
reset_ops = [v.initializer for v in my_metric_variables]
with tf.Session() as sess:
tf.local_variables_initializer().run()
for _ in range(100):
for _ in range(100):
sess.run(update_op)
print(sess.run(mean_x))
# if you comment the following out, the estimate of the mean converges to 0
sess.run(reset_ops)
如果要重置其内部变量,则可以调用tf.contrib.eager.metrics
的指标(无论是否执行都可以工作)具有init_variable()
操作。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.