python - 在 tensorflow 中重置图表

Question

我有一个巨大全局变量，用于训练和评估但具有不同的形状。现在我尝试在同一个过程中同时运行评估和训练，我偶然发现我无法真正删除 tensorflow 图中定义的变量。建议的解决方法例如 here是使用 reset_default_graph() 但这似乎与图形上下文管理器无关。

import numpy as np
import tensorflow as tf

GRAPH = tf.Graph()

def train(examples):
    with GRAPH.as_default() as g:
        # actually this is huge variable
        global_var = tf.get_variable('global_var',
                                     initializer=np.full((examples, 32), 0.0),
                                     trainable=False)

def evaluate(examples):
    # tf.reset_default_graph() # ValueError: Variable input_var already exists
    with GRAPH.as_default() as g: # initialized to some other size
        tf.reset_default_graph() 
        global_var = tf.get_variable('global_var',
                                     initializer=np.full((examples, 32), 0.0),
                                     trainable=False)
       # in fact tensorflow creates a new graph and does not use GRAPH to define global_var

train(32)
evaluate(8)

结果:

Traceback (most recent call last):
  File "C:/Users/MrD/.PyCharm2017.1/config/scratches/scratch_44.py", line 22, in <module>
    evaluate(8)
  File "C:/Users/MrD/.PyCharm2017.1/config/scratches/scratch_44.py", line 19, in evaluate
    trainable=False)
  File "C:\_\Python35\lib\contextlib.py", line 66, in __exit__
    next(self.gen)
  File "C:\_\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 3616, in get_controller
    if self.stack[-1] is not default:
IndexError: list index out of range

那么使用 reset_default_graph() 的正确方法是什么？真的没有办法重新定义一个 Variable 来丢弃旧的可能巨大的初始值设定项吗？

Answer 1

事实证明，在图上下文管理器中“重置默认图”没有意义 - 请参阅:https://github.com/tensorflow/tensorflow/issues/11121 .较新的版本应该添加更有用的错误消息:

AssertionError: Do not use tf.reset_default_graph() to clear nested graphs. If you need a cleared graph, exit the nesting and create a new graph.

如上期所述并实现 here