如何修复“运行时错误：会话图为空”。在调用 run() 之前向图中添加操作。”

Question

我只是简单地输入了tf.Tensor Tensorflow 2.0 中给出的代码，这是我的代码：

import tensorflow as tf
print(tf.__version__)
# Build a dataflow graph.
c = tf.constant([[1.0, 2.0], [3.0, 4.0]])
d = tf.constant([[1.0, 1.0], [0.0, 1.0]])
e = tf.matmul(c, d)

# Construct a `Session` to execute the graph.
sess = tf.compat.v1.Session()

# Execute the graph and store the value that `e` represents in `result`.
result = sess.run(e)

但它引发了一个错误：

2.0.0-beta1
2019-07-25 17:06:35.972372: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Traceback (most recent call last):
  File "/Users/yupng/Documents/Dissertation/kmnist/kminst_v1.0.py", line 14, in <module>
    result = sess.run(e)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 950, in run
    run_metadata_ptr)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1098, in _run
    raise RuntimeError('The Session graph is empty.  Add operations to the '
RuntimeError: The Session graph is empty.  Add operations to the graph before calling run().

Process finished with exit code 1

我能做些什么来修复这个错误？

Answer 1

TF 2.0 支持急切执行，这意味着您不必显式创建会话并在其中运行代码。所以最简单的解决方案是：

import tensorflow as tf
print(tf.__version__)

# Build a dataflow graph.
c = tf.constant([[1.0, 2.0], [3.0, 4.0]])
d = tf.constant([[1.0, 1.0], [0.0, 1.0]])
e = tf.matmul(c, d)

print(e)

哪个输出

2.0.0-beta1
tf.Tensor(
[[1. 3.]
 [3. 7.]], shape=(2, 2), dtype=float32)

但是，如果您愿意，您可以使用会话：

2.0.0-beta1
tf.Tensor(
[[1. 3.]
 [3. 7.]], shape=(2, 2), dtype=float32)

这使

2.0.0-beta1
[[1. 3.]
 [3. 7.]]

Answer 2

TensorFlow 2.0 默认启用了 Eager Execution。在算法开始时，您需要使用tf.compat.v1.disable_eager_execution()来禁用 Eager Execution。

import tensorflow as tf

tf.compat.v1.disable_eager_execution()

print(tf.__version__)

# Build a dataflow graph.
c = tf.constant([[1.0, 2.0], [3.0, 4.0]])
d = tf.constant([[1.0, 1.0], [0.0, 1.0]])
e = tf.matmul(c, d)

# Construct a `Session` to execute the graph.
sess = tf.compat.v1.Session()

# Execute the graph and store the value that `e` represents in `result`.
result = sess.run(e)
print(result)

输出给出：

2.1.0
[[1. 3.]
 [3. 7.]]