TypeError: An op outside of the function building code is being passed a "Graph" tensor.

[Tipper-sun]

my problem:
TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
@tf.function
def has_init_scope():
my_constant = tf.constant(1.)
with tf.init_scope():
added = my_constant * 2
The graph tensor has name: block1_conv1/kernel:0

[nacayu]

https://blog.csdn.net/sinat_28494049/article/details/104663053
Some strange problems you can search on google first, this mignt be version setting problem