Windows上的Tensorflow量化

Question

I've freezed my model and got .pb file. Then I've quantize my model using tocoConverter on Linux, as it's not supported on Windows. I've got quantized_model.tflite. I can load it and get predictions on Linux, but I have issues to make it on Windows, as my project requires. I've tried to load it using tf.contrib.lite.Interpreter using this code:

import numpy as np
import tensorflow as tf

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

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

# Test model on random input data.
input_shape = input_details[0]['shape']
# change the following line to feed into your own data.
input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
interpreter.set_tensor(input_details[0]['index'],input_data)

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

*ImportError: No module named 'tensorflow.contrib.lite.python.Interpreter*

But it failed with "No module named 'tensorflow.contrib.lite.python.interpreter" error. I always get this errors on Windows, when trying to use something from tf.contrib.lite. Maybe there is a way to load this on Windows? Or can you advice alternative options to quantize a model on Windows?

Answer 1

toco is currently not supported on Windows build for cmake. This is what I remember reading somewhere.