[英]Getting Error while converting tensorflow model to tensorflow lite = ValueError: bad marshal data (unknown type code)
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我正在使用预先训练的基于 keras 和基于 tensorflow 的模型与 yolov2 架构进行坑洼检测,在将我的 tensorflow 模型转换为 tensorflow lite 时出现错误
Error = ValueError: bad marshal data (unknown type code)错误 = ValueError:错误的封送数据(未知类型代码)
I'm using tensorflow 1.3 and keras 2.0.8.我正在使用 tensorflow 1.3 和 keras 2.0.8。 This is my code:这是我的代码:
converter = lite.TFLiteConverter.from_keras_model_file(keras_file)
tflite_model = converter.convert()
open("trained_wts.tflite","wb").write(tflite_model)
Please provide more information.请提供更多信息。
The error was on the last line, but there was no reference on how to get marshal
object and how to get raw_code
.错误在最后一行,但没有关于如何获取marshal
对象以及如何获取raw_code
。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.