Convert kTfLiteFloat32 input tensor from kotlin project

I’m in study how to deploy model to android app.
But i meet some question about mobilenetv2.tflite. I have spend a lots of time to fix it that still doesn’t work… :face_with_head_bandage: :yum: :face_with_head_bandage:

Could you help me?

The question detail is below:

And the error details:

Hi @Jin_Au-Yeung, If you are using task library The ImageClassifier API expects a TFLite model with mandatory TFLite Model Metadata. See examples of creating metadata for image classifiers using the TensorFlow Lite Metadata Writer API. Thank You.

The model detail is below:
https://tfhub.dev/google/lite-model/imagenet/mobilenet_v3_small_100_224/classification/5/default/1

if you need any info please let me know, thanks!

OK, let me try! thank you very much :handshake:

Surprisingly, it worked!!.
Thank you very much. Although I don’t know why I must bring Metadata, I think I should read its documentation carefully.