Python 如何在Tensorflow中使用采样的最大损耗

我是tensorflow的初学者。我已经建立了简单的模型，但还没有尝试过类似多层LSTM的东西，因此非常感谢任何反馈：）

我目前正试图从头开始重新编写由构建的字符级模型，原因很简单，因为我想知道如何使用tensorflow（我之前已经按照cs231n的分配构建了自己的非常小的DL库）。现在，我正在努力构建一个简单的2层LSTM模型，但不确定到底出了什么问题。以下是我迄今为止编写的代码：

class Model():
    def __init__(self, batch_size, seq_length, lstm_size, num_layers, grad_clip, vocab_size):
        self.lr = tf.Variable(0.0, trainable=False)        

        #Define input and output
        self.input_data = tf.placeholder(tf.float32, [batch_size, seq_length])
        self.output_data = tf.placeholder(tf.float32, [batch_size, seq_length]) #although int would be better for character level..

        #Define the model
        cell = tf.nn.rnn_cell.BasicLSTMCell(num_units=lstm_size) #can choose if basic or otherwise later on...
        self.cell = cell = rnn_cell.MultiRNNCell([cell] * num_layers)
        self.initial_state = cell.zero_state(batch_size, tf.float32)


        with tf.variable_scope("lstm"):
            softmax_w = tf.get_variable("softmax_w", [lstm_size, vocab_size])
            softmax_b = tf.get_variable("softmax_b", [vocab_size])

        #_, enc_state = rnn.rnn(cell, encoder_inputs, dtype=dtype)
        #outputs, states = rnn_decoder(decoder_inputs, enc_state, cell)


        outputs, states = seq2seq.basic_rnn_seq2seq(
                            [self.input_data],
                            [self.output_data], 
                            cell,
                            scope='lstm'
                        )


        #see how attention helps improving this model state...

        #was told that we should actually use samples softmax loss
        self.loss = tf.nn.sampled_softmax_loss(
                                    softmax_w, 
                                    softmax_b,
                                    outputs, 
                                    self.output_data,
                                    batch_size,
                                    vocab_size
                )

我现在遇到了tf.nn.sampled_softmax_损失的问题。我在调试方面走了很长的路，不理解Tensorflow的输入约定。我每次都要输入张量列表吗

我得到以下错误：

Traceback (most recent call last):
  File "Model.py", line 76, in <module>
vocab_size=82
  File "Model.py", line 52, in __init__
vocab_size
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/nn.py", line 1104, in sampled_softmax_loss
name=name)
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/nn.py", line 913, in _compute_sampled_logits
array_ops.expand_dims(inputs, 1),
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 506, in expand_dims
return _op_def_lib.apply_op("ExpandDims", input=input, dim=dim, name=name)
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/op_def_library.py", line 411, in apply_op
as_ref=input_arg.is_ref)
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 566, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/constant_op.py", line 179, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/constant_op.py", line 162, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape))
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 332, in make_tensor_proto
_AssertCompatible(values, dtype)
  File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 269, in _AssertCompatible
    raise TypeError("List of Tensors when single Tensor expected")
TypeError: List of Tensors when single Tensor expected

---

此外，如果我有任何其他错误等，请让我在评论中知道！这是我在tensorflow中使用seq2seq模型的第一个模型，因此非常感谢您的建议

这个特殊的错误是关于传递

输出

，这是一个列表，需要一个张量

该函数返回大小为

[batch\u size x output\u size]

的张量列表作为第一个输出。假设每个输出都是一维的，您希望使用（创建大小为

[seq\u len x batch\u size x 1]

的张量）、最后一个维度（结果为

[seq\u len x batch\u size]

）连接输出列表，并使

输出具有大小
[batch\u size x seq\u len]
，与
self.output\u data
相同

要调试此问题，请使用
print（output.get_shape（））
打印张量大小

Model = Model(batch_size=32, 
              seq_length=128, 
              lstm_size=512, 
              num_layers=2, 
              grad_clip=5,
              vocab_size=82
             )