Question

我对模块tf.metrics的函数返回的值有点困惑（例如tf.metrics.accuracy）。

一段简单的代码，我使用tf.metrics.accuracy并使用tp，tn，fp和fn来计算准确度。

import tensorflow as tf

# true and predicted tensors
y_p = tf.placeholder(dtype=tf.int64)
y_t = tf.placeholder(dtype=tf.int64)

# Count true positives, true negatives, false positives and false negatives.
tp = tf.count_nonzero(y_p * y_t)
tn = tf.count_nonzero((y_p - 1) * (y_t - 1))
fp = tf.count_nonzero(y_p * (y_t - 1))
fn = tf.count_nonzero((y_p - 1) * y_t)

acc = tf.metrics.accuracy(y_p, y_t)

# Calculate accuracy, precision, recall and F1 score.
accuracy = (tp + tn) / (tp + fp + fn + tn)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    sess.run(tf.local_variables_initializer())

    for i in range(4):
        if i == 0:
            yop = [0,0,0,0,0,0,0,0,0,0]
        elif i == 1:
            yop = [0,0,0,0,0,0,0,0,1,1]
        elif i == 2:
            yop = [1,1,1,0,0,0,0,0,0,1]
        else:
            yop = [0,1,1,1,1,1,1,0,0,0]
        tf_a = sess.run(acc, feed_dict={y_p: [0,0,0,0,0,0,0,0,0,0], y_t: yop})
        my_a = sess.run(accuracy, feed_dict={y_p: [0,0,0,0,0,0,0,0,0,0], y_t: yop})
        print("TF accuracy: {0}".format(tf_a))
        print("My accuracy: {0}".format(my_a))

输出

TF accuracy: (0.0, 1.0)
My accuracy: 1.0
TF accuracy: (1.0, 0.9)
My accuracy: 0.8
TF accuracy: (0.9, 0.8)
My accuracy: 0.6
TF accuracy: (0.8, 0.7)
My accuracy: 0.4

据我所知，tf.metrics.accuracy（update_op）的第二个返回值是调用函数的平均精度。但是，我无法理解第一个值，它应该代表准确性。为什么它与我自己计算的准确度值不同？有没有办法获得准确度的非累积值？

提前致谢。

Answer 1

import tensorflow as tf
from sklearn.metrics import accuracy_score

# true and predicted tensors
y_p = tf.placeholder(dtype=tf.int64)
y_t = tf.placeholder(dtype=tf.int64)

# Count true positives, true negatives, false positives and false negatives.
tp = tf.count_nonzero(y_p * y_t)
tn = tf.count_nonzero((y_p - 1) * (y_t - 1))
fp = tf.count_nonzero(y_p * (y_t - 1))
fn = tf.count_nonzero((y_p - 1) * y_t)

acc = tf.metrics.accuracy(predictions=y_p, labels=y_t)

# Calculate accuracy, precision, recall and F1 score.
accuracy = (tp + tn) / (tp + fp + fn + tn)

with tf.Session() as sess:
    for i in range(4):
        sess.run(tf.global_variables_initializer())
        sess.run(tf.local_variables_initializer())


        if i == 0:
            yop = [0,0,0,0,0,0,0,0,0,0]
        elif i == 1:
            yop = [0,0,0,0,0,0,0,0,1,1]
        elif i == 2:
            yop = [1,1,1,0,0,0,0,0,0,1]
        else:
            yop = [0,1,1,1,1,1,1,0,0,0]
        print('accuracy_score', accuracy_score([0,0,0,0,0,0,0,0,0,0], yop))
        tf_a = sess.run(acc, feed_dict={y_p: [0,0,0,0,0,0,0,0,0,0], y_t: yop})
        my_a = sess.run(accuracy, feed_dict={y_p: [0,0,0,0,0,0,0,0,0,0], y_t: yop})
        print("TF accuracy: {0}".format(tf_a))
        print("My accuracy: {0}".format(my_a))
        print()

输出：

accuracy_score 1.0
TF accuracy: (0.0, 1.0)
My accuracy: 1.0

accuracy_score 0.8
TF accuracy: (0.0, 0.8)
My accuracy: 0.8

accuracy_score 0.6
TF accuracy: (0.0, 0.6)
My accuracy: 0.6

accuracy_score 0.4
TF accuracy: (0.0, 0.4)
My accuracy: 0.4

只需移动循环内的tf.local_variables_initializer()，即可确保精度度量张量值重新初始化。

为什么会有效？

根据文件

精确度函数创建两个局部变量，total和count 用于计算预测匹配的频率标签

如果我们不重新初始化局部变量，那么前一次迭代的值仍保留在其中，导致您遇到错误的结果。

另一种方法是使用：

tf.contrib.metrics.accuracy代替tf.metrics.accuracy。但是这会在最后给出一些剩余价值，例如0.800000011920929而不是0.8。正如OP在评论中指出的那样，它也是deprecated。

来源：

https://www.tensorflow.org/api_docs/python/tf/metrics/accuracy

https://github.com/tensorflow/tensorflow/issues/3971

How to properly use tf.metrics.accuracy?

张量流精度度量返回的值的含义

1 个答案: