.lite 和 .tflite 格式有什么区别 [英] What is the difference between the .lite and the .tflite formats

问题描述

.lite 和 .tflite 格式(TensorFlow 格式)有什么区别?如果没有区别，为什么会有两个?

What is the difference between the .lite and the .tflite formats (TensorFlow formats)? And if there is no difference, why there are two of them?

除了问题之外，我似乎无法将带有 .lite 扩展文件的模型上传到 Firebase ML 套件.这可能是什么原因?

In addition to the question, it seems that I can't upload my model with the .lite extension file to Firebase ML kit. What might be the reason for that?

推荐答案

ML 开发者首先训练一个 TensorFlow 模型，然后使用 TOCO 将其转换为 TensorFlow Lite 模型.运行 TOCO 命令时，您可以为转换后的 Lite 模型指定任何输出名称.所有 TensorFlow Lite TOCO 示例都使用 .tflite 扩展名；但 .lite 似乎是人们想要选择的另一个流行扩展名.

ML Developers first train a TensorFlow model, and then use TOCO to convert it to TensorFlow Lite model. When running the TOCO command, you can specify whatever output name for the converted Lite model. All TensorFlow Lite TOCO samples use .tflite extension; but .lite seems another popular extension people would like to choose.

因此，只要是 TensorFlow Lite FlatBuffer 格式的模型，TensorFlow Lite 就可以加载/运行模型，而不管扩展名如何.

So as long as it's a TensorFlow Lite FlatBuffer formatted model, TensorFlow Lite would be able to load / run the model regardless of the extension.

但不幸的是，此时 ML Kit 控制台只接收扩展名为 .tflite 的文件.我们可以考虑取消强制执行.同时，如果您确定它是 TensorFlow Lite 模型，只需重命名扩展程序并上传即可.

But unfortunately, ML Kit Console at this moment only takes files with .tflite extension. We can consider remove that enforcement. In the meantime, if you are sure it's a TensorFlow Lite model, simply rename the extension and upload it.

这篇关于.lite 和 .tflite 格式有什么区别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！