[英]Tensorflow Object Detection API: how to find out false positives, false negatives, true positives?
I am using Tensorflow Object Detection API to finetune a pretrained model from the model zoo for custom object detection. 我正在使用Tensorflow对象检测API来微调来自模型动物园的预训练模型以进行自定义对象检测。 Once my model is converged I use
eval_util.py
with EvalConfig.metrics_set='open_images_V2_detection_metrics'
to obtain the mAP
(and class-specific AP
s) which lets me measure the quality of my model. 模型融合后,我可以将
eval_util.py
与EvalConfig.metrics_set='open_images_V2_detection_metrics'
以获取mAP
(以及特定于类的AP
),从而可以mAP
模型的质量。
But just mAP
is not enough for my purposes. 但是
mAP
点不足以达到我的目的。 For better analysis, I want to know the exact breakdown of my model's results into false positives, false negatives and true positives. 为了进行更好的分析,我想知道模型结果分为误报,误报和真报的确切细分。 I wish to be able to see this breakdown in terms of actual test images - that is, I want to see my test images being physically divided into those three groups, automatically.
我希望能够以实际测试图像的形式查看此细分-也就是说,我希望看到测试图像在物理上自动地自动分为这三个组。
How can I do that? 我怎样才能做到这一点?
I tried searching through Tensorflow's offical documentation and, to some extent, through the relevant python files on github, but I haven't found a way yet. 我尝试搜索Tensorflow的官方文档,并在某种程度上搜索github上的相关python文件,但是我还没有找到解决方法。
I think what you are looking for is a confusion matrix. 我认为您正在寻找的是混乱矩阵。 Take a look at this link: Tensorflow Confusion Matrix
看一下此链接: Tensorflow混淆矩阵
You can basically evaluate your predictions with this function. 您基本上可以使用此功能评估您的预测。
We also meet this problem. 我们也遇到这个问题。 Now we find some clues in object_detection/utils/metrics.py.
现在,在object_detection / utils / metrics.py中找到一些线索。 Maybe you can have a try.
也许您可以尝试一下。 Hope you can share your solutions!
希望您能分享您的解决方案!
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.