Login Register

tf.contrib.learn.monitors.ValidationMonitor.best_value

tf.contrib.learn.monitors.ValidationMonitor.best_value

Returns the best early stopping metric value found so far.

Links:

https://www.tensorflow.org/versions/master/api_docs/python/contrib.learn.monitors.html#ValidationMonitor.best_value

doc_TensorFlow

2016-10-14 13:06:47

Comments

Leave a Comment

Please login to continue.

Popular Articles

tf.contrib.learn.monitors.ValidationMonitor.best_step tf.contrib.learn.monitors.ValidationMonitor.best_step Returns the step at which the best early stopping metric was found.

tf.contrib.learn.monitors.ValidationMonitor class tf.contrib.learn.monitors.ValidationMonitor Runs evaluation of a given estimator, at most every N steps. Note that the evaluation is done base

tf.contrib.learn.monitors.ValidationMonitor.__init__() tf.contrib.learn.monitors.ValidationMonitor.__init__(x=None, y=None, input_fn=None, batch_size=None, eval_steps=None, every_n_steps=100, metrics=Non

tf.contrib.learn.monitors.ValidationMonitor.begin() tf.contrib.learn.monitors.ValidationMonitor.begin(max_steps=None) Called at the beginning of training. When called, the default graph is the one we

tf.contrib.learn.monitors.ValidationMonitor.end() tf.contrib.learn.monitors.ValidationMonitor.end(session=None)