TFLiteConverter on tensorflow 1.14 in raspberry pi 3b+

Question

I have a code for convert tflite. it is the code:

 from tensorflow import lite
from tensorflow.keras              

import models
# Parameters
keras_model_filename =         

'wake_word_stop_model.h5'
tflite_filename =     'wake_word_stop_lite.tflite'

# Convert model to TF Lite   

 model
 model =   models.load_model(keras_model_     filename)
converter       
   =lite.TFLiteConverter.from_keras_model(model)
tflite_model =           
converter.convert()
 open(tflite_filename,     
'wb').write(tflite_model

''' but this code error. with message AttributeError: type object 'TFLiteConverter' has no attribute 'from_keras_model'

Answer 1

from_keras_model is an API of Tensorflow 2.x

You could use from_keras_model_file API

But I'd suggest to consider an upgrade to 2.x version