最近迁移项目出现的问题:
方案1:
Using the TensorFlow documentation for tf.name_scope, I resolved the issue by prepending [x] with values=. That is change with tf.name_scope(“Encoder_resnet”, [x]): to with tf.name_scope(“Encoder_resnet”, values=[x]):. This error also occurs in a few places over in batch_lbs.py which I fixed in the same way.
就是多加一个 values= 就可以了
tf.name_scope(“Encoder_resnet”, [x]) -------》tf.name_scope(“Encoder_resnet”, values=[x])
方案2:方案1太过麻烦,所以推荐2
降低tensorflow的版本,我是降到1.3.0版本,把这个bug给解决了