TensorFlow获得单次预测精度

Question

我使用TensorFlow和MNIST数据集实现了一个logistic回归模型。我想出了如何使用以下代码获得学习算法的总精度...

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

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

这工作良好，打印精度为91%。现在我正在恢复模型，并将单个图像传递到模型中以进行预测。我传递了一张数字7的图片，mnist.test.images[0]，它正确地预测了它->[7]...

with tf.Session() as sess:
    saver.restore(sess, "/tmp/model.ckpt")
    x_in = np.expand_dims(mnist.test.images[0], axis=0)
    classification = sess.run(tf.argmax(pred, 1), feed_dict={x:x_in})
    print(classification)

现在我想要得到这个预测的准确性与模型的关系，但我不确定如何继续，我尝试了以下显然不起作用的...

 accuracy = tf.reduce_mean(tf.cast(classification, tf.float32))
 print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

Answer 1

with tf.Session() as sess:
    saver.restore(sess, "/tmp/model.ckpt")
    x_in = np.expand_dims(mnist.test.images[0], axis=0)
    y_in = np.expand_dims(mnist.test.labels[0], axis=0)
    print("Accuracy:", accuracy.eval({x: x_in , y: y_in}))