我遇到以下问题：我需要组合的CNN-LSTM体系结构的中间输出，即CNN输出的编码图像。显然，不启动会话并初始化变量就无法获得张量值。但是，由于未初始化的值，在我的代码中启动tensorflow会话始终会产生错误。我做了很多实验，仅使用常规/交互式会话等初始化局部/全局变量。但是，似乎没有任何效果，代码会挂起或立即产生错误。有谁知道如何解决这个问题？
非常感谢！
更新：因此，当前使我无法运行成功会话的问题是
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'image_feed' with dtype string
[[node image_feed (defined at /Documents/im2txt/bazel-bin/im2txt/run_inference.runfiles/im2txt/im2txt/show_and_tell_model.py:133) ]]
...
File "/Documents/im2txt/bazel-bin/im2txt/run_inference.runfiles/im2txt/im2txt/show_and_tell_model.py", line 133, in build_inputs
image_feed = tf.compat.v1.placeholder(dtype=tf.string, shape=[], name="image_feed")
File "/anaconda3/envs/workenv_p2/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 2143, in placeholder
return gen_array_ops.placeholder(dtype=dtype, shape=shape, name=name)
File "/anaconda3/envs/workenv_p2/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 6262, in placeholder
"Placeholder", dtype=dtype, shape=shape, name=name)
File "/anaconda3/envs/workenv_p2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/anaconda3/envs/workenv_p2/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/anaconda3/envs/workenv_p2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/anaconda3/envs/workenv_p2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2005, in __init__
self._traceback = tf_stack.extract_stack()
但是，第133行明确指出了
image_feed = tf.compat.v1.placeholder(dtype=tf.string, shape=[], name="image_feed")