[Python] Tensorflow Lite (LiteRn) Deployment in Android using Kotlin, Error 'FULLY_CONNECTED'...

I am trying to integrate deep learning model to my android application. But I am getting stucked on running the model in my application.

I have created a model that uses tensorflow for detecting the object. For model building I have used the following versions : python => 3.11.11 tensorflow => 2.17.0

Similarly, in Android side, I have used the following compatible libraries tensorflow Lite => 2.17.0 tensorflow Lite Gpu => 2.17.0 tensorflow Lite Task Vision => 0.4.4

Also I have used following to convert the tensorflow to liteRn model

converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
converter.optimizations = [tf.lite.Optimize.DEFAULT]
tflite_model = converter.convert()


But still I am getting the following error

Didn't find op for builtin opcode 'FULLY_CONNECTED' version '12'. An older version of this builtin might be supported. Are you using an old TFLite binary with a newer model?

Error getting native address of native library: task_vision_jni
java.lang.IllegalArgumentException: Error occurred when initializing ImageClassifier: Didn't find op for builtin opcode 'FULLY_CONNECTED' version '12'. An older version of this builtin might be supported. Are you using an old TFLite binary with a newer model?




I found some solution in
Internal error: Cannot create interpreter: Didn't find op for builtin opcode 'FULLY_CONNECTED' version '9' with firebase ml kit and tensorflow-lite

but it didn't help me specially for Verison 12

Can any please help me to identify the error and solve this problem ? Thank you for your time and support.

Continue reading...