将 tensorflow 模型转换为 tensorflow lite = ValueError: bad marshal data (unknown type code) 时出错

Question

I am using a pre-trained keras based and tensorflow based model with yolov2 architecture for potholes detection and I'm getting an error while converting my tensorflow model to tensorflow lite

Error = ValueError: bad marshal data (unknown type code)

I'm using tensorflow 1.3 and keras 2.0.8. This is my code:

converter = lite.TFLiteConverter.from_keras_model_file(keras_file) 
tflite_model = converter.convert()
open("trained_wts.tflite","wb").write(tflite_model)

Answer 1

Please provide more information.

The error was on the last line, but there was no reference on how to get marshal object and how to get raw_code .