我正在尝试为时间序列分析制作一个 Seq2Seq 回归示例，并且我使用了 Dev Summit 上介绍的 Seq2Seq 库，该库目前是 Tensorflow GitHub 分支 r1.0 上的代码。
我很难理解解码器功能如何用于 Seq2Seq，特别是“cell_output”。
我知道 num_decoder_symbols 是每个时间步要解码的类/单词的数量。我让它在我可以进行培训的时候工作。但是，我不明白为什么不能只用特征数量 (num_features) 代替 num_decoder_symbols。基本上，我希望能够在没有教师强制的情况下运行解码器，换句话说，将上一个时间步的输出作为下一个时间步的输入传递。
with ops.name_scope(name, "simple_decoder_fn_inference",
[time, cell_state, cell_input, cell_output,
context_state]):
if cell_input is not None:
raise ValueError("Expected cell_input to be None, but saw: %s" %
cell_input)
if cell_output is None:
# invariant that this is time == 0
next_input_id = array_ops.ones([batch_size,], dtype=dtype) * (
start_of_sequence_id)
done = array_ops.zeros([batch_size,], dtype=dtypes.bool)
cell_state = encoder_state
cell_output = array_ops.zeros([num_decoder_symbols],
dtype=dtypes.float32)
为什么我不需要为单元格输出传递 batch_size？
cell_output = array_ops.zeros([batch_size, num_decoder_symbols],
dtype=dtypes.float32)
当尝试使用此代码创建我自己的回归 Seq2Seq 示例时，我没有输出概率/类，而是有一个维度为 num_features 的实值向量，而不是类概率数组。据我了解，我认为我可以用 num_features 替换 num_decoder_symbols，如下所示：
def decoder_fn(time, cell_state, cell_input, cell_output, context_state):
"""
Again same as in simple_decoder_fn_inference but for regression on sequences with a fixed length
"""
with ops.name_scope(name, "simple_decoder_fn_inference", [time, cell_state, cell_input, cell_output, context_state]):
if cell_input is not None:
raise ValueError("Expected cell_input to be None, but saw: %s" % cell_input)
if cell_output is None:
# invariant that this is time == 0
next_input = array_ops.ones([batch_size, num_features], dtype=dtype)
done = array_ops.zeros([batch_size], dtype=dtypes.bool)
cell_state = encoder_state
cell_output = array_ops.zeros([num_features], dtype=dtypes.float32)
else:
cell_output = output_fn(cell_output)
done = math_ops.equal(0,1) # hardcoded hack just to properly define done
next_input = cell_output
# if time > maxlen, return all true vector
done = control_flow_ops.cond(math_ops.greater(time, maximum_length),
lambda: array_ops.ones([batch_size,], dtype=dtypes.bool),
lambda: done)
return (done, cell_state, next_input, cell_output, context_state)
return decoder_fn
但是，我收到以下错误：
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/contrib/seq2seq/python/ops/seq2seq.py", line 212, in dynamic_rnn_decoder
swap_memory=swap_memory, scope=scope)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 1036, in raw_rnn
swap_memory=swap_memory)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2605, in while_loop
result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2438, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2388, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 980, in body
(next_output, cell_state) = cell(current_input, state)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/contrib/rnn/python/ops/core_rnn_cell_impl.py", line 327, in __call__
input_size = inputs.get_shape().with_rank(2)[1]
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/framework/tensor_shape.py", line 635, in with_rank
raise ValueError("Shape %s must have rank %d" % (self, rank))
ValueError: Shape (100,) must have rank 2
结果，我像这样传递了 batch_size 以获得排名 2 的形状：
cell_output = array_ops.zeros([batch_size, num_features],
dtype=dtypes.float32)
但是我收到以下错误，其中 Shape 的排名为 3，而想要排名为 2：
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/contrib/seq2seq/python/ops/seq2seq.py", line 212, in dynamic_rnn_decoder
swap_memory=swap_memory, scope=scope)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 1036, in raw_rnn
swap_memory=swap_memory)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2605, in while_loop
result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2438, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2388, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 980, in body
(next_output, cell_state) = cell(current_input, state)
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/contrib/rnn/python/ops/core_rnn_cell_impl.py", line 327, in __call__
input_size = inputs.get_shape().with_rank(2)[1]
File "/opt/DL/tensorflow/lib/python2.7/site-packages/tensorflow/python/framework/tensor_shape.py", line 635, in with_rank
raise ValueError("Shape %s must have rank %d" % (self, rank))
ValueError: Shape (10, 10, 100) must have rank 2