[英]What would be minimum SDK(Software Development Kit) level in Android Studio for making a Machine Learning model based application
Basically, I have to make ML-based application in Android Studio.
基本上,我必须在 Android Studio 中制作基于 ML 的应用程序。 I already make and trained my ML model and converted it into the TensorFlow Lite model.
我已经制作并训练了我的 ML model 并将其转换为 TensorFlow Lite model。 But when it comes to the android studio while configuring my project there's an option for minimum SDK.
但是当谈到 android 工作室时,在配置我的项目时,有一个最小 SDK 的选项。 As far as I know, you have to select the minimum SDK level so that your application can run on every android version.
据我所知,您必须将 select 设为最低 SDK 级别,以便您的应用程序可以在每个 android 版本上运行。 In that case, how can I ensure that ML-based application will work fine on the older android version?
在这种情况下,我如何确保基于 ML 的应用程序可以在较旧的 android 版本上正常工作? This is the reason I am asking what would be the minimum SDK level for ML-based application.
这就是我问基于 ML 的应用程序的最低 SDK 级别的原因。
minimum SDK level is used to determine minimum API you want your application to support.最低 SDK 级别用于确定您希望应用程序支持的最低 API。 It doesn't quite related to your tflite model.
它与您的 tflite model 不太相关。
I think what's most important is that you pull in correct tflite runtime which has all ops that your model uses.我认为最重要的是您引入了正确的 tflite 运行时,其中包含 model 使用的所有操作。
Not sure whether you model has metadata.不确定您的 model 是否有元数据。 If it does, maybe you can use ml model binding so you don't need write too many boilerplate code.
如果是这样,也许您可以使用ml model 绑定,这样您就不需要编写太多样板代码。
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.