ValueError：形状 (None, 12, 2) 和 (None, 12) 不兼容

Question

谁能帮帮我，我的形状有什么问题。我正在研究分层文本分类，共有 12 个类，即 3 个类别和 9 个子类别。当我尝试对我的数据运行 LSTM 时，它适用于 3 个类别，但是当我通过这两个类别时。即两列。我正面临这个错误。

Epoch 1/50
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-176-8c3ffb5351b5> in <module>
----> 1 LSTM_model.fit(X_train,y_train, epochs=50,batch_size=32)

D:\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

D:\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1096                 batch_size=batch_size):
   1097               callbacks.on_train_batch_begin(step)
-> 1098               tmp_logs = train_function(iterator)
   1099               if data_handler.should_sync:
   1100                 context.async_wait()

D:\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    778       else:
    779         compiler = "nonXla"
--> 780         result = self._call(*args, **kwds)
    781 
    782       new_tracing_count = self._get_tracing_count()

D:\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    821       # This is the first call of __call__, so we have to initialize.
    822       initializers = []
--> 823       self._initialize(args, kwds, add_initializers_to=initializers)
    824     finally:
    825       # At this point we know that the initialization is complete (or less

D:\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
    695     self._concrete_stateful_fn = (
    696         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 697             *args, **kwds))
    698 
    699     def invalid_creator_scope(*unused_args, **unused_kwds):

D:\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2853       args, kwargs = None, None
   2854     with self._lock:
-> 2855       graph_function, _, _ = self._maybe_define_function(args, kwargs)
   2856     return graph_function
   2857 

D:\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3211 
   3212       self._function_cache.missed.add(call_context_key)
-> 3213       graph_function = self._create_graph_function(args, kwargs)
   3214       self._function_cache.primary[cache_key] = graph_function
   3215       return graph_function, args, kwargs

D:\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3073             arg_names=arg_names,
   3074             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3075             capture_by_value=self._capture_by_value),
   3076         self._function_attributes,
   3077         function_spec=self.function_spec,

D:\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    984         _, original_func = tf_decorator.unwrap(python_func)
    985 
--> 986       func_outputs = python_func(*func_args, **func_kwargs)
    987 
    988       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

D:\anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    598         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    599         # the function a weak reference to itself to avoid a reference cycle.
--> 600         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    601     weak_wrapped_fn = weakref.ref(wrapped_fn)
    602 

D:\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    971           except Exception as e:  # pylint:disable=broad-except
    972             if hasattr(e, "ag_error_metadata"):
--> 973               raise e.ag_error_metadata.to_exception(e)
    974             else:
    975               raise

ValueError: in user code:

    D:\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function  *
        return step_function(self, iterator)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    D:\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    D:\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    D:\anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step  **
        outputs = model.train_step(data)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:749 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\engine\compile_utils.py:204 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\losses.py:149 __call__
        losses = ag_call(y_true, y_pred)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\losses.py:253 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    D:\anaconda3\lib\site-packages\tensorflow\python\util\dispatch.py:201 wrapper
        return target(*args, **kwargs)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\losses.py:1535 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    D:\anaconda3\lib\site-packages\tensorflow\python\util\dispatch.py:201 wrapper
        return target(*args, **kwargs)
    D:\anaconda3\lib\site-packages\tensorflow\python\keras\backend.py:4687 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    D:\anaconda3\lib\site-packages\tensorflow\python\framework\tensor_shape.py:1134 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 12, 2) and (None, 12) are incompatible

相关代码为：

LSTM_model=Sequential()
LSTM_model.add(LSTM(18,activation='relu',input_shape=X_train[0,:,:].shape))
LSTM_model.add(Dropout(0.5))
LSTM_model.add(Dense((12), activation='softmax'))
opt = keras.optimizers.Adam(learning_rate=0.001)
LSTM_model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer=opt)
LSTM_model.fit(X_train,y_train, epochs=50,batch_size=32)

这是我的数据的形状

X_train.shape
(42098, 20, 100)

y_train.shape
(42098, 12, 2)

总结

LSTM_model.summary()
Model: "sequential_56"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_55 (LSTM)               (None, 18)                8568      
_________________________________________________________________
dropout_54 (Dropout)         (None, 18)                0         
_________________________________________________________________
dense_50 (Dense)             (None, 12)                228       
=================================================================
Total params: 8,796
Trainable params: 8,796
Non-trainable params: 0

Answer 1

正如您从错误消息中看到的那样，模型需要一个二维数组作为输入，其第二维的形状是 12。由于您没有提供您正在处理的数据的一瞥，我只是从现在开始推测在。我认为您的数据的第三个轴是 12 个类值中的每一个的一个热表示。如果是这种情况，您可以使用整数编码将多维 one-hot 表示转换为一维表示。一旦你的第三个轴的大小为 1（当你得到一个形状为 (42098, 12, 1) 的数组时），你就可以将它重塑为 (42098, 12)。

换句话说，您应该摆脱y_train 变量的第三维。你应该怎么做取决于你的数据是什么编码的。