Question

我想使用以下代码计算预测：

import tensorflow as tf

x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])

pred = multilayer_perceptron(x, weights, biases)


cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Initializing the variables

##trn.txt start

##tst.txt end
with tf.Session() as sess:
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(num_lines_trn/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_x, batch_y = bat_x[i*batch_size:(i+1)*batch_size],bat_y[i*batch_size:(i+1)*batch_size]#mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
                                                          y: batch_y})
            # Compute average loss
            avg_cost += c / total_batch

    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))

    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

    print(sess.run(accuracy, feed_dict={x: tst_x, y: tst_y}))
    print(sess.run(accuracy, feed_dict={x: tst_x}))

该行

print(sess.run(accuracy, feed_dict={x: tst_x, y: tst_y}))

返回0.80353，这是批次的准确性。

但是我想获得预测结果。所以我补充说：

print(sess.run(accuracy, feed_dict={x: tst_x}))

但是这一行会返回一个错误：

您必须为占位符张量提供一个值＆＃39; Placeholder_7＆＃39;同 dtype float

我该如何解决这个问题？

Answer 1

如果您想获得模型的预测，您应该这样做：

sess.run(pred, feed_dict={x: tst_x})

您遇到错误，因为您尝试运行sess.run(accuracy, feed_dict={x: tst_x})，但要计算给定批次的准确性，您需要占位符y中包含的真实标签，因此您会收到以下错误：< / p>

您必须为占位符张量值'占位符名称y'
提供值

tensorflow如何获得预测

1 个答案: