Question

Tensorflow具有计算AUC的功能：tf.metrics.auc（）。这是我的一段代码试图计算auc：

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(training_epochs):
        sess.run(optimizer, feed_dict = {x : x_train, y : y_train, p_keep_input: 0.8, p_keep_hidden: 0.5})
        avg_cost = sess.run(cost, feed_dict = {x : x_train, y : y_train, p_keep_input: 0.8, p_keep_hidden: 0.5})

        if epoch % display_step == 0:
            training_acc = accuracy.eval({x : x_train, y : y_train, p_keep_input: 1.0, p_keep_hidden: 1.0})
            print("Epoch:", '%03d' % (epoch), "Training Accuracy:", '%.5f' % (training_acc), "cost=", "{:.5f}".format(avg_cost))

    print("Optimization Done!")


    roc_score = tf.metrics.auc(y, pred)
    roc_score = tf.convert_to_tensor(roc_score)
    print(roc_score.eval({x : x_test, y : y_test, p_keep_input: 1.0, p_keep_hidden: 1.0}))

我得到的错误的任何部分如下。整个错误非常冗长。

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value auc_4/false_positives
     [[Node: auc_4/false_positives/read = Identity[T=DT_FLOAT, _class=["loc:@auc_4/false_positives"], _device="/job:localhost/replica:0/task:0/cpu:0"](auc_4/false_positives)]]

我很感激有关如何解决这个问题的任何指示。感谢

Answer 1

现在可能为时已晚，但如果您还没有找到解决方案，请尝试此更改：

sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
_,roc_score = tf.metrics.auc(y, pred)
print(sess.run(roc_score, feed_dict={x : x_test, y : y_test, p_keep_input: 1.0, p_keep_hidden: 1.0}))

似乎无法让Tensorflow的tf.metrics.auc正常工作

1 个答案: