使用InceptionV3在单个图像上进行预测时尝试使用未初始化的值错误

Question

我想使用https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/label_image/label_image.py上可用的tensorflow的label_image.py来对微调的inceptionV3进行预测。

但是我遇到以下错误

Error creating bean with name 'customScopedClass' :  Scope 'customScope' is not active for the current thread; consider defining a scoped proxy for this bean if you intend to refer to it from a singleton

我已使用此https://github.com/tensorflow/models/tree/master/research/inception教程对InceptionV3模型进行了微调。

我已使用本教程https://github.com/deep-machine-learning/Retrained-InceptionV3/blob/master/freeze_graph.py

冻结了模型以创建Frozen_model.pb文件。