我正在尝试使用 Tensorflow 1.3.0 实现用于文本摘要的 seq2seq 模型。
我尝试在编码层使用MultiRNNCell和bi Direction_dynamic_rnn。我丢失了一些东西，但无法找到它。错误堆栈跟踪并不直接，这使得它更难以理解。
我在构建图表时遇到以下错误。
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in _call_cpp_shape_fn_impl(op, input_tensors_needed, input_tensors_as_shapes_needed, require_shape_fn)
653 graph_def_version, node_def_str, input_shapes, input_tensors,
--> 654 input_tensors_as_shapes, status)
655 except errors.InvalidArgumentError as err:
~/anaconda2/envs/tensorflow/lib/python3.5/contextlib.py in __exit__(self, type, value, traceback)
65 try:
---> 66 next(self.gen)
67 except StopIteration:
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
465 compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466 pywrap_tensorflow.TF_GetCode(status))
467 finally:
InvalidArgumentError: Dimensions must be equal, but are 512 and 256 for 'decoding/decoder/while/BasicDecoderStep/decoder/multi_rnn_cell/cell_0/cell_0/basic_lstm_cell/mul' (op: 'Mul') with input shapes: [?,512], [?,256].
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-119-85ee67bc88e5> in <module>()
9 # Create the training and inference logits
10 training_logits, inference_logits = seq2seq_model(input_,target,embeding_matrix,vocab_to_int,source_seq_length,target_seq_length,
---> 11 max_target_seq_length,rnn_size,keep_probability,num_layers,batch_size)
12
13 # Create tensors for the training logits and inference logits
<ipython-input-114-5ad1bf459bd7> in seq2seq_model(source_input, target_input, embeding_matrix, vocab_to_int, source_sequence_length, target_sequence_length, max_target_length, rnn_size, keep_prob, num_layers, batch_size)
15 training_logits, inference_logits = decoding_layer(target_input,encoder_states,embedings,
16 vocab_to_int,rnn_size,target_sequence_length,
---> 17 max_target_length,batch_size,num_layers)
18
19 return training_logits, inference_logits
<ipython-input-113-c2b4542605d2> in decoding_layer(target_inputs, encoder_state, embedding, vocab_to_int, rnn_size, target_sequence_length, max_target_length, batch_size, num_layers)
12
13 training_logits = training_decoder(embed,decoder_cell,encoder_state,output_layer,
---> 14 target_sequence_length,max_target_length)
15
16
<ipython-input-117-012bbcdcf997> in training_decoder(dec_embed_input, decoder_cell, encoder_state, output_layer, target_sequence_length, max_target_length)
17
18 final_outputs, final_state = tf.contrib.seq2seq.dynamic_decode(decoder=decoder,impute_finished=True,
---> 19 maximum_iterations=max_target_length)
20
21 return final_outputs
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/seq2seq/python/ops/decoder.py in dynamic_decode(decoder, output_time_major, impute_finished, maximum_iterations, parallel_iterations, swap_memory, scope)
284 ],
285 parallel_iterations=parallel_iterations,
--> 286 swap_memory=swap_memory)
287
288 final_outputs_ta = res[1]
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in while_loop(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, name)
2773 context = WhileContext(parallel_iterations, back_prop, swap_memory, name)
2774 ops.add_to_collection(ops.GraphKeys.WHILE_CONTEXT, context)
-> 2775 result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
2776 return result
2777
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in BuildLoop(self, pred, body, loop_vars, shape_invariants)
2602 self.Enter()
2603 original_body_result, exit_vars = self._BuildLoop(
-> 2604 pred, body, original_loop_vars, loop_vars, shape_invariants)
2605 finally:
2606 self.Exit()
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in _BuildLoop(self, pred, body, original_loop_vars, loop_vars, shape_invariants)
2552 structure=original_loop_vars,
2553 flat_sequence=vars_for_body_with_tensor_arrays)
-> 2554 body_result = body(*packed_vars_for_body)
2555 if not nest.is_sequence(body_result):
2556 body_result = [body_result]
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/seq2seq/python/ops/decoder.py in body(time, outputs_ta, state, inputs, finished, sequence_lengths)
232 """
233 (next_outputs, decoder_state, next_inputs,
--> 234 decoder_finished) = decoder.step(time, inputs, state)
235 next_finished = math_ops.logical_or(decoder_finished, finished)
236 if maximum_iterations is not None:
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/seq2seq/python/ops/basic_decoder.py in step(self, time, inputs, state, name)
137 """
138 with ops.name_scope(name, "BasicDecoderStep", (time, inputs, state)):
--> 139 cell_outputs, cell_state = self._cell(inputs, state)
140 if self._output_layer is not None:
141 cell_outputs = self._output_layer(cell_outputs)
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/rnn_cell_impl.py in __call__(self, inputs, state, scope)
178 with vs.variable_scope(vs.get_variable_scope(),
179 custom_getter=self._rnn_get_variable):
--> 180 return super(RNNCell, self).__call__(inputs, state)
181
182 def _rnn_get_variable(self, getter, *args, **kwargs):
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/layers/base.py in __call__(self, inputs, *args, **kwargs)
448 # Check input assumptions set after layer building, e.g. input shape.
449 self._assert_input_compatibility(inputs)
--> 450 outputs = self.call(inputs, *args, **kwargs)
451
452 # Apply activity regularization.
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/rnn_cell_impl.py in call(self, inputs, state)
936 [-1, cell.state_size])
937 cur_state_pos += cell.state_size
--> 938 cur_inp, new_state = cell(cur_inp, cur_state)
939 new_states.append(new_state)
940
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/rnn_cell_impl.py in __call__(self, inputs, state, scope)
772 self._recurrent_input_noise,
773 self._input_keep_prob)
--> 774 output, new_state = self._cell(inputs, state, scope)
775 if _should_dropout(self._state_keep_prob):
776 new_state = self._dropout(new_state, "state",
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/rnn_cell_impl.py in __call__(self, inputs, state, scope)
178 with vs.variable_scope(vs.get_variable_scope(),
179 custom_getter=self._rnn_get_variable):
--> 180 return super(RNNCell, self).__call__(inputs, state)
181
182 def _rnn_get_variable(self, getter, *args, **kwargs):
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/layers/base.py in __call__(self, inputs, *args, **kwargs)
448 # Check input assumptions set after layer building, e.g. input shape.
449 self._assert_input_compatibility(inputs)
--> 450 outputs = self.call(inputs, *args, **kwargs)
451
452 # Apply activity regularization.
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/rnn_cell_impl.py in call(self, inputs, state)
405
406 new_c = (
--> 407 c * sigmoid(f + self._forget_bias) + sigmoid(i) * self._activation(j))
408 new_h = self._activation(new_c) * sigmoid(o)
409
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py in binary_op_wrapper(x, y)
863 else:
864 raise
--> 865 return func(x, y, name=name)
866
867 def binary_op_wrapper_sparse(sp_x, y):
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py in _mul_dispatch(x, y, name)
1086 is_tensor_y = isinstance(y, ops.Tensor)
1087 if is_tensor_y:
-> 1088 return gen_math_ops._mul(x, y, name=name)
1089 else:
1090 assert isinstance(y, sparse_tensor.SparseTensor) # Case: Dense * Sparse.
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py in _mul(x, y, name)
1447 A `Tensor`. Has the same type as `x`.
1448 """
-> 1449 result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
1450 return result
1451
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py in apply_op(self, op_type_name, name, **keywords)
765 op = g.create_op(op_type_name, inputs, output_types, name=scope,
766 input_types=input_types, attrs=attr_protos,
--> 767 op_def=op_def)
768 if output_structure:
769 outputs = op.outputs
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in create_op(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_shapes, compute_device)
2630 original_op=self._default_original_op, op_def=op_def)
2631 if compute_shapes:
-> 2632 set_shapes_for_outputs(ret)
2633 self._add_op(ret)
2634 self._record_op_seen_by_control_dependencies(ret)
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in set_shapes_for_outputs(op)
1909 shape_func = _call_cpp_shape_fn_and_require_op
1910
-> 1911 shapes = shape_func(op)
1912 if shapes is None:
1913 raise RuntimeError(
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in call_with_requiring(op)
1859
1860 def call_with_requiring(op):
-> 1861 return call_cpp_shape_fn(op, require_shape_fn=True)
1862
1863 _call_cpp_shape_fn_and_require_op = call_with_requiring
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in call_cpp_shape_fn(op, require_shape_fn)
593 res = _call_cpp_shape_fn_impl(op, input_tensors_needed,
594 input_tensors_as_shapes_needed,
--> 595 require_shape_fn)
596 if not isinstance(res, dict):
597 # Handles the case where _call_cpp_shape_fn_impl calls unknown_shape(op).
~/anaconda2/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py in _call_cpp_shape_fn_impl(op, input_tensors_needed, input_tensors_as_shapes_needed, require_shape_fn)
657 missing_shape_fn = True
658 else:
--> 659 raise ValueError(err.message)
660
661 if missing_shape_fn:
ValueError: Dimensions must be equal, but are 512 and 256 for 'decoding/decoder/while/BasicDecoderStep/decoder/multi_rnn_cell/cell_0/cell_0/basic_lstm_cell/mul' (op: 'Mul') with input shapes: [?,512], [?,256].
我无法理解这个错误。它试图引用哪个矩阵？请帮助我，我对 Tensorflow 还很陌生。
最佳答案
该错误表示解码器的 LSTM 内部 (decoding/decoder/while/BasicDecoderStep/decoder/multi_rnn_cell/cell_0/cell_0/basic_lstm_cell/mul) 在乘法期间存在维度不匹配 ( 相乘)。
我的猜测是，对于您的实现，由于您使用的是双向编码器，因此解码器 LSTM 需要的单元数量是编码器 LSTM 的两倍。如果您有一个带有 256 个单元的 LSTM 的双向编码器，那么结果将有 512 个单元(当您连接前向和后向 LSTM 的输出时)。目前解码器似乎期望输入 256 个单元。
关于python - ValueError : Dimensions must be equal, 但分别是 512 和 256，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/46015362/