是否可以扩展 python imageai 预训练 model 以获得更多类？
[英]Is it possible to extend python imageai pretrained model for more classes?
问题描述
I am working on a project which uses imageai with YOLOv3 which works fast and accurately for my purpose.
我正在开发一个项目，该项目使用带有 YOLOv3 的 imageai，它可以快速准确地用于我的目的。 However this model is able to detect only 80 classes out of which I want some of them but want to add some more classes as well.然而，这个 model 只能检测到 80 个类，我想要其中的一些，但也想添加更多类。 I referred to https://imageai.readthedocs.io/en/latest/customdetection/index.html to train my own custom model with 3 more classes.我参考了https://imageai.readthedocs.io/en/latest/customdetection/index.html来训练我自己的自定义 model 更多的课程。 However, I am unable to detect the 80 classes that were provided by YOLOv3.但是，我无法检测到 YOLOv3 提供的 80 个类。 Is there a way to generate a model that extends the existing YOLOv3 and can detect all 80 classes + extra classes that I want?有没有办法生成一个 model 扩展现有的 YOLOv3 并且可以检测我想要的所有 80 个类 + 额外的类？
PS I am new to tensorflow and imageai so I don't know too much. PS 我是 tensorflow 和 imageai 的新手，所以我不太了解。 Please bear with me.请多多包涵。
1 个解决方案
解决方案1
0 2022-07-19 14:43:47
I have not yet found a way to extend an existing model, but i can assure you that training your own model is far more efficient than using all the classes noones wants.我还没有找到扩展现有 model 的方法，但我可以向你保证，训练你自己的 model 比使用没有人想要的所有课程更有效。 If it still interests you, this person had a different question: Loading a trained Keras model and continue training如果您仍然感兴趣，此人有一个不同的问题： 加载经过训练的 Keras model 并继续训练
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.