오류 질문있습니다.

[syssjh]

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: batch_normalization/gamma:0

에포크마다 값들은 출력되는데 그래프가 생성되지 않고 오류가 뜨네요.
해결방법 좀 알려주실 수 있을까요?
[Epoch 001/100] Epsilon:1.0000 #Expl.:243/243 #Buy:70 #Sell:41 #Hold:132 #Stocks:259 PV:13,203,985 LC:14 Loss:39.900025 ET:3.4939

[quantylab]

@syssjh tensorflow 버전을 알려주시면 이슈 해결에 도움이 될 것 같습니다.

import tensorflow; tensorflow.__version__