tflite_inference.py

# https://www.tensorflow.org/lite/guide/inference#load_and_run_a_model_in_python

#Simple version
interpreter = tf.lite.Interpreter(model_path='./upsampling_float.tflite')
interpreter.allocate_tensors()

interpreter.set_tensor(interpreter.get_input_details()[0]['index'], sample_input )
interpreter.invoke()

output_tflite_float = interpreter.get_tensor(output_details[0]['index'])[0]

##################################################
interpreter = tf.lite.Interpreter(model_path='./model_quant.tflite')

#           (batch_size, height, width, channels)
input_shape = (32, 224, 224, 3)

# Adjust graph input to handle batch tensor
interpreter.resize_tensor_input(input_details[0]['index'], input_shape)

# 2 outputs 
interpreter.resize_tensor_input(output_details[0]['index'], output_shape1)
interpreter.resize_tensor_input(output_details[1]['index'], output_shape2)

interpreter.allocate_tensors()

#get input and output tensors
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

#set the tensor to point to the input data to be inferred
input_index = interpreter.get_input_details()[0]['index']

interpreter.set_tensor(input_index, input_tensor )

#Run the inference
interpreter.invoke()

prediction1 = interpreter.get_tensor(output_details[0]['index'])[0]
prediction2 = interpreter.get_tensor(output_details[1]['index'])[0]

print(prediction)