Question

我编写了以下Tensorflow代码，该代码对自定义数据集执行逻辑回归。

def logi_regression(data, labels, test_data, test_labels, learning_rate, 
                batch_size, training_epochs, display_step):

x = tf.placeholder(tf.float32, [None, data.shape[1]])
y = tf.placeholder(tf.float32, [None, labels.shape[1]])

# Weights
W = tf.Variable(tf.zeros([data.shape[1], 1]))
b = tf.Variable(tf.zeros([1, 1]))

# Logistic Model
pred = tf.nn.sigmoid(tf.matmul(x, W) + b)

# Error function
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=pred, 
                                                              labels=y))

# Gradient Descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)

# Initialise global variables
init = tf.global_variables_initializer()
init_l = tf.local_variables_initializer()

# Training
with tf.Session() as sess:

    # Run the initializer
    sess.run(init)
    sess.run(init_l)
    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(data.shape[0]/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            # The next_data_batch is a custom made function
            batch_xs, batch_ys = next_data_batch(batch_size, 
                                                 data, labels)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, loss], feed_dict={x: batch_xs,
                                                          y: batch_ys})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print("Optimization Finished!")

    # Test model
    prediction = tf.round(tf.sigmoid(pred))
    correct = tf.cast(tf.equal(prediction, y), dtype=tf.float32)
    _, precision = tf.metrics.precision(y, prediction)
    # Calculate accuracy
    accuracy = tf.reduce_mean(correct)
    avg_prec = tf.reduce_mean(precision)
    print("Accuracy:", accuracy.eval({x: test_data, y: test_labels}))
    print("Average Precision Score:", avg_prec.eval({x: test_data, y: test_labels}))

但是，即使我从训练（Epoch: xxxx cost= 0.xxxx）和测试集（Accuracy:0.xxx）获得了正确的输出。当程序尝试计算精度时，它将返回错误：

FailedPreconditionError（请参阅上面的回溯）：尝试使用未初始化的值precision / true_positives / count [[node precision / true_positives / AssignAdd（定义在：54）]]

因此，问题出在我添加了（{_, precision = tf.metrics.precision(y, prediction)）的最后几行中。我已经尝试过Stackoverflow帖子中的各种建议，但没有任何效果。这肯定是一个愚蠢的编码错误，但是由于我对Tensorflow的经验不足，所以我无法弄清楚它是什么。

Answer 1

在tensorflow-graph中创建节点的线应在'tf.global_variables_initializer（）'语句之前，作为默认图的一部分。将以下几行移至初始化程序上方，它将起作用：

# Test model
    prediction = tf.round(tf.sigmoid(pred))
    correct = tf.cast(tf.equal(prediction, y), dtype=tf.float32)
    _, precision = tf.metrics.precision(y, prediction)
    # Calculate accuracy
    accuracy = tf.reduce_mean(correct)
    avg_prec = tf.reduce_mean(precision)

Tensorflow精度指标未初始化

1 个答案: