tflite1.py

import re
import numpy as np
import tensorflow as tf

e = [
    3080192,
    3801088,
    3702784,
    4325376,
    4587520,
    4784128,
    4620288,
    4653056,
    4390912,
    4096000,
    3932160,
    3899392,
    4390912,
    4423680,
    4259840,
    5308416,
    5275648,
    5079040,
    5013504,
    4259840,
    4554752,
    5472256,
    6946816,
    7274496,
    6717440,
    6881280,
    5308416,
    4751360,
    5111808,
    5013504,
    5832704,
    5996544,
    7077888,
    6356992,
    5931008,
    5341184,
    4390912,
    2654208,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0
]

y = [
    5931008,
    5308416,
    5013504,
    3473408,
    3637248,
    3964928,
    3342336,
    3178496,
    3899392,
    4194304,
    4096000,
    3604480,
    3768320,
    4128768,
    4259840,
    3735552,
    3276800,
    4554752,
    4390912,
    4194304,
    3932160,
    4227072,
    4325376,
    3997696,
    3506176,
    3014656,
    2752512,
    655360,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0,
    0
]

# Load TFLite model and allocate tensors.
interpreter = tf.contrib.lite.Interpreter(model_path="model1.tflite")
interpreter.allocate_tensors()

# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
print(input_details)
# Test model on random input data.
input_shape = input_details[0]['shape']
# input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
# input_data = e
# input_data = [e]
# input_data = [e[0]]
# for i in (range(len(y) - 1)):
#     interpreter.set_tensor(input_details[i]['index'], [y[i]])
indices = [0] * 51
for detail in input_details:
    vindex = 0
    m = re.match(r'Const_(\d+)', detail['name'])
    if (m is None):
        vindex = 0
    else:
        vindex = int(m.group(1))
    indices[vindex] = detail['index']

for i in range(len(e)-1):
    interpreter.set_tensor(indices[i], [e[i]])

interpreter.invoke()
output_data = interpreter.get_tensor(output_details[0]['index'])
print(output_data)