问题描述
我是神经网络的新手,并为初学者学习了 MNIST 示例.
I am new to Neural Networks and went through the MNIST example for beginners.
我目前正在尝试在另一个没有测试标签的 Kaggle 数据集上使用这个例子.
I am currently trying to use this example on another dataset from Kaggle that does not have test labels.
如果我在没有相应标签的测试数据集上运行模型,因此无法像 MNIST 示例中那样计算准确度,我希望能够看到预测.是否有可能以某种方式访问观察结果及其预测标签并将其打印出来?
If I run the model on the test data set without corresponding labels and therefore unable to compute the accuracy like in the MNIST example, I would like to be able to see the predictions. Is it possible to access observations and their predicted labels somehow and print them out nicely?
推荐答案
我认为你只需要按照教程中的说明评估你的输出张量:
I think you just need to evaluate your output-tensor as stated in the tutorial:
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
要获取张量的输出,请参阅文档:
To get the output of a tensor see the docs:
在会话中启动图形后,可以通过将其传递给 Session.run() 来计算张量的值.t.eval() 是调用 tf.get_default_session().run(t).
如果你想得到预测而不是准确性,你需要以同样的方式评估你的输出张量 y
:
If you want to get predictions rather than accuracy, you need to evaluate your ouput tensor y
in the same way:
print(sess.run(y, feed_dict={x: mnist.test.images}))
这篇关于如何在 TensorFlow 的 MNIST 示例中获得预测的类标签?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!