如何用我自己的 tflite 替换 Tensorflow 的 Android 图像分类示例中的 tflite？

Question

I cloned the Tensorflow's Android image classification example and I want to now use my own tflite that I have downloaded from here to classify food. How do I replace the default tflites with my own tflite? I only have one tflite while in the Android example there's a couple so I'm not sure which tflite to get rid of.

Answer 1

First, add the model into the assets folder. Alternatively, you can directly download the model from TFHub in the similar way as the models in download.gradle .

Then if you use Task library to run inference (which is simpler), you will need to add a similar class of ClassifierFloatEfficientNet.java and provide the model info. Register your new class in Classifier.java .

If you use the TFLite Support library to run inference, you'll add the new class like this one .