问题描述
我尝试遵循tensorflow API 1.4文档来实现我在学习过程中需要的东西.
I try to follow the tensorflow API 1.4 document to achieve what I need in a learning process.
我现在处于这个阶段，可以产生一个预测对象，例如:
I am now at this stage, can produce a predict object for example:
classifier = tf.estimator.DNNClassifier(feature_columns=feature_cols,hidden_units=[10, 20, 10], n_classes=3, model_dir="/tmp/xlz_model")
predict = classifier.predict(input_fn=input_pd_fn_prt (test_f),predict_keys=["class_ids"])
label =tf.constant(test_l.values, tf.int64)
例如，如何在tf.metrics.auc中使用预测和标签:
how can I use predict and label in tf.metrics.auc for example:
out, opt = tf.metrics.auc(label, predict)
我尝试了很多不同的选择.没有明确的文档应该如何使用这些tensorflow API.
I have tried so many different options. there are no clear documentation how these tensorflow APIs can be should be used.
推荐答案
该函数返回2个操作:
auc, update_op = tf.metrics.auc(...)
如果运行sess.run(auc)，您将取回当前的auc值.这是您要报告的值，例如print sess.run([auc, cost], feed_dict={...}).
If you run sess.run(auc) you will get back the current auc value. This is the value you want to report on, for example, print sess.run([auc, cost], feed_dict={...}).
可能需要通过多次调用sess.run来计算AUC度量.例如，当您要计算AUC的数据集不适合内存时.这就是update_op的来源.您需要每次都调用它来累积计算auc所需的值.
The AUC metric may need to be computed over many calls to sess.run. For example, when the dataset you're computing the AUC for doesn't fit in memory. That's where the update_op comes in. You need to call it each time to accumulate the values needed to compute auc.
因此，在测试集评估期间，您可能会遇到以下问题:
So during a test set evaluation, you might have this:
for i in range(num_batches):
sess.run([accuracy, cost, update_op], feed_dict={...})
print("Final (accumulated) AUC value):", sess.run(auc))
当您想重置累积值时(例如，在重新评估测试集之前)，应重新初始化局部变量. tf.metrics软件包明智地将其累加器变量添加到局部变量集合中，该局部变量集合默认不包括权重之类的可训练变量.
When you want to reset the accumulated values (before you re-evaluate your test set, for example) you should re-initialize your local variables. The tf.metrics package wisely adds its accumulator variables to the local variables collection, which don't include trainable variables such as weights by default.
sess.run(tf.local_variables_initializer()) # Resets AUC accumulator variables
https://www.tensorflow.org/api_docs/python/tf /metrics/auc
这篇关于如何在估算器模型中使用tf.metrics .__预测输出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！