【问题标题】:tensorflow lite conversion failed. "undefined symbol : _ZTIN10tensorflow6DeviceE" occuredtensorflow lite 转换失败。 “未定义符号:_ZTIN10tensorflow6DeviceE”发生
【发布时间】:2020-04-16 19:37:31
【问题描述】:
tflite_model = converter.convert()
tflite_model_file = 'converted_model.tflite'

with open(tflite_model_file, "wb") as f:
  f.write(tflite_model)

当我最终在点转换方法中转换模型时, 我遇到了一些错误。

错误信息:

ValueError: Failed to parse the model: /tensorflow-2.1.0/python3.6/tensorflow_core/lite/python/optimize/_tensorflow_lite_wrap_calibration_wrapper.so: undefined symbol: _ZTIN10tensorflow6DeviceE.

源代码:

https://colab.research.google.com/github/tensorflow/examples/blob/master/courses/udacity_intro_to_tensorflow_lite/tflite_c02_transfer_learning.ipynb#scrollTo=BbTF6nd1KG2o

即使我没有找到是什么

_ZTIN10tensorflow6DeviceE

如何转换迁移学习模型?

【问题讨论】:

    标签: tensorflow tensorflow-lite transfer-learning


    【解决方案1】:

    我遇到了同样的问题 - 安装 nightly build(当前为“2.1.0-dev20200104”)解决了它。

    !pip3 uninstall tensorflow
    !pip3 install tf-nightly
    

    【讨论】:

      猜你喜欢
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 2021-06-10
      • 2019-10-16
      • 2017-05-20
      • 2019-11-06
      • 1970-01-01
      • 2018-09-07
      相关资源
      最近更新 更多