【问题标题】:NotFoundError: Container localhost does not exist. (Could not find resource: localhost/embedding_1/embeddings)NotFoundError:容器本地主机不存在。 (找不到资源:localhost/embedding_1/embeddings)
【发布时间】:2020-08-25 03:50:41
【问题描述】:

我有一个非常简单的代码,我想在其中添加嵌入,但出现错误。我想查看嵌入输出。

我的代码:

input_question_ = Input((query_maxlen,))
embedded_question = Embedding(vocab_size, embedding_dim)(input_question_)

sess = tf.Session()

sess.run(embedded_question, feed_dict={ input_question_: queries_train})

错误:

---------------------------------------------------------------------------
NotFoundError                             Traceback (most recent call last)
~/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py

在 _do_call(self, fn, *args) 1364 尝试: -> 1365 返回 fn(*args) 1366 除了errors.OpError as e:

~/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py

在 _run_fn(feed_dict, fetch_list, target_list, options, run_metadata) 第1349章 -> 1350 目标列表,运行元数据) 第1351章

~/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py

在 _call_tf_sessionrun(self, options, feed_dict, fetch_list, 目标列表,运行元数据) 第1442章 -> 1443 运行元数据) 第1444章

NotFoundError: Container localhost does not exist. (Could not find resource: localhost/embedding_1/embeddings)
   [[{{node embedding_1/embedding_lookup}}]]

During handling of the above exception, another exception occurred:

NotFoundError                             Traceback (most recent call last)
<ipython-input-95-bf218d6ed295> in <module>
     39 sess = tf.Session()
     40 
---> 41 sess.run(embedded_question, feed_dict={ input_question_: queries_train})

~/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py

在运行中(self、fetches、feed_dict、options、run_metadata) 954尝试: 第955章 --> 956 run_metadata_ptr) 957 如果运行元数据: 958 proto_data = tf_session.TF_GetBuffer(运行元数据ptr)

~/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py

in _run(self, handle, fetches, feed_dict, options, run_metadata) 1178 如果 final_fetches 或 final_targets 或(句柄和 feed_dict_tensor): 1179 结果 = self._do_run(句柄,final_targets,final_fetches, -> 1180 feed_dict_tensor,选项,run_metadata) 1181 其他: 1182 个结果 = []

~/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py

在 _do_run(self, handle, target_list, fetch_list, feed_dict, options, 运行元数据) 1357 如果句柄为无: 第1358章 -> 1359 运行元数据) 1360 其他: 第1361章

~/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py

在 _do_call(self, fn, *args) 第1382章 第1383章 -> 1384 提升类型(e)(node_def,op,消息) 1385 第1386章

NotFoundError: Container localhost does not exist. (Could not find resource: localhost/embedding_1/embeddings)
   [[node embedding_1/embedding_lookup (defined at /home/mzaman/miniconda2/envs/py3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748)

]]

寻求解决方案

【问题讨论】:

    标签: tensorflow embedding


    【解决方案1】:

    您似乎缺少对创建模型的 Tensorflow 会话的引用。试试:

    import numpy as np
    import tensorflow as tf
    
    query_maxlen = 100
    vocab_size = 500
    embedding_dim = 32
    input_question = tf.keras.layers.Input((query_maxlen,))
    embedded_question = tf.keras.layers.Embedding(vocab_size, embedding_dim)(input_question)
    
    sess = tf.keras.backend.get_session()
    
    output = sess.run(
        embedded_question, feed_dict={input_question: np.ones((1, query_maxlen))}
    )
    assert (1, 100, 32) == output.shape
    print(output)
    

    相关问题: Container localhost does not exist error when using Keras + Flask Blueprints

    【讨论】:

      猜你喜欢
      • 2014-02-08
      • 1970-01-01
      • 1970-01-01
      • 2012-07-26
      • 2021-08-20
      • 2014-01-26
      • 2012-05-19
      • 2020-06-02
      • 2019-11-09
      相关资源
      最近更新 更多