quick_run.py

import numpy as np 
import sys
from tflite_runtime.interpreter import Interpreter
from tflite_runtime.interpreter import load_delegate
import time

if len(sys.argv) < 2:
    print('Usage:', sys.argv[0], 'model_path')
    exit()

def main():
    """Runs inference with an input tflite model.""" 
    model_path = str(sys.argv[1])
    if model_path.endswith('edgetpu.tflite'):
        print('initialized for edgetpu')
        delegates = [load_delegate('libedgetpu.so.1.0')]                             
        interpreter = Interpreter(model_path, experimental_delegates=delegates)
    else: 
        print('initialized for cpu')
        interpreter = Interpreter(model_path)

    interpreter.allocate_tensors() 
    input_details = interpreter.get_input_details()
    images = np.zeros(input_details[0]['shape'], input_details[0]['dtype'])
    #print(images)
    interpreter.set_tensor(input_details[0]['index'], images)
    t0 = time.perf_counter()
    for i in range(1000):
      interpreter.invoke()
    print('time took for 1000 invokes:', time.perf_counter() - t0)
    output_details = interpreter.get_output_details() 
    outputs = interpreter.get_tensor(output_details[0]['index']) 
    print(outputs)
    print('Success.') 

if __name__== '__main__':
    main()