Question

我是Python的新手并使用Tensorflow，但现在我只是尝试从here实现基本的Word2Vec教程。

它的代码如下：

  with tf.device('/cpu:0'):
    embeddings = tf.Variable(
        tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
    embed = tf.nn.embedding_lookup(embeddings, train_inputs)

当我运行with tf.device部分时，它会输出此错误：

 File "<ipython-input-26-83a85a16701d>", line 1

    with tf.device('/cpu:0'):

    SyntaxError: unexpected EOF while parsing

当我运行整个块时，它会输出

Traceback (most recent call last):


 File "<ipython-input-23-79908ea0756f>", line 5, in <module>
    embed = tf.nn.embedding_lookup(embeddings, train_inputs)

 File "...\Anaconda3\lib\site-packages\tensorflow\python\ops\embedding_ops.py", line 100, in embedding_lookup
    with ops.name_scope(name, "embedding_lookup", params + [ids]) as name:

  File "...\Anaconda3\lib\contextlib.py", line 59, in `__enter__`
    return next(self.gen)


 File "...\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 4055, in name_scope
    g = _get_graph_from_inputs(values)


  File "...\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3804, in _get_graph_from_inputs
    _assert_same_graph(original_graph_element, graph_element)


 File "...\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3743, in _assert_same_graph
    "%s must be from the same graph as %s." % (item, original_item))


ValueError: Tensor("Placeholder_2:0", shape=(128,), dtype=int32) must be from the same graph as Tensor("Variable_6:0", shape=(50000, 128), dtype=float32_ref, device=/device:CPU:0).

以前谢谢！

Tensorflow：使用CPU tf.device进行解析时出现意外的EOF

0 个答案: