Tensorflow模型精度 [英] Tensorflow model accuracy

问题描述

我的模型在一组29K图像上训练了36个类，并在7K图像上进行了验证。该模型的训练准确度为94.59％，验证准确度为95.72％
它是针对数字和字符的OCR创建的。我知道在36个班级上训练的图像数量可能还不够。我不确定从这些结果中可以推断出什么。

My model which I have trained on a set of 29K images for 36 classes and validated on 7K images. The model has a training accuracy of 94.59% and validation accuracy of 95.72% It has been created for OCR on digits and characters. I know the amount of images for training on 36 classes might not be sufficient. I'm not certain what to infer from these results.

问题：这是一个很好的结果吗？测试精度是否应始终大于训练精度？我的模型是否过拟合？

Question: Is this a good result? Should the testing accuracy always be greater than training accuracy? Is my model overfitting?

问题：我怎么知道我的模型是否过拟合？我假设非常高的培训准确性和非常低的测试准确性表明了这一点？

Question: How would I know if my model was overfitting? I'm assuming a very high training accuracy and very low testing accuracy would indicate that?

推荐答案

1. 95％对于36个类来说相当不错。如果您的验证准确性高于训练准确性，则说明您不合格。您可以再运行几个纪元，直到您的训练精度比验证精度高 。


2. 确实，如果训练精度高得多，您就过度拟合了。

这篇关于Tensorflow模型精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！