深度学习预测温度 [英] Deep learning to predict the temperature

问题描述

假设我有一个训练数据.我针对1,2,3,4,5度的整数温度训练模型.基本上，这些输出温度是标签.如何预测介于两个温度(例如2.5度)之间的值.不可能针对每个温度值进行训练.我该如何实现?

Let's say I have a training data. I train the model for whole number temperatures like 1,2,3,4,5 degrees. Basically, Those output temperatures are the labels. How can I predict the values that lies between two temperatures like 2.5 degree. It is not possible to train for every values of temperature. How can I achieve this?

推荐答案

它好像已经训练成离散分类，但是却想要连续输出，因此很容易受伤.切换算法以进行回归，而不是分类.

It wounds as if you've trained to a discrete classification, but you want continuous output. Switch your algorithm to do regression, rather than classification.

另一种可能性是利用您的最后一层输出进行插值.使用赋予最优先选择权和最强邻近选择权的权重.例如，如果您的分类给出

Another possibility is to harness your last-layer output to interpolate. Use the weights given to the top choice and its strongest adjacent choice. For instance, if your classification gives

1  .01
2  .05
3  .56
4  .24
5  .14

...您将对56个部分3和24个部分4进行插值，以得到3.7 degrees作为您的输出.

... you would interpolate with 56 parts 3 and 24 parts 4, to get 3.7 degrees as your output.

有帮助吗?

更新

(1)如何从分类切换到回归?

对于堆栈溢出来说，这个范围太广了；您需要先进行研究.两者之间的区别并非微不足道.您需要提出一个具体的问题，这需要发布一个新问题，其中包括您当前的代码以及您进行切换的工作.

This is far too broad for Stack Overflow; you need to do your research first. The difference between the two is not trivial. You would need to ask a specific question, which requires posting a new question that includes your current code and your work toward making the switch.

(2)当我根据输出预测值时，如何知道我正在寻找3.7度...?

在预测时，您不会知道；那将是培训的问题.我举的例子只是一个可能结果的说明.我发明了一个示例，因为您没有提供有关数据的详细信息.

While you're predicting, you don't know; that would have been an issue for training. The example I gave is just an illustration of a possible result. I invented an example, since you gave no details on your data.

(3)我应该选择哪个部分?

我建议您最先猜测(这将是您的整数值分类)，并且比较有可能使用相邻的值.在我的示例中，3是最常见的猜测.您查看2和4，发现4比2更有可能，因此将4用作插值的另一个端点.

I recommended that you take the top guess (the one that would have been your integer-value classification), and the more probable of the adjacent values. In my example, 3 is the top guess. You look at 2 and 4, and see the 4 is more likely than 2, so use 4 for the interpolation's other endpoint.

这篇关于深度学习预测温度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IT屋！