拟合我的自定义模型后的值错误

Question

我正在时尚 MNIST 数据集上创建一个编码器。编码器由三层组成，每张输入图像被展平为784维。这三个编码器的输出维数分别为128、64、32。但是在拟合模型后，它抛出了一个值错误-ValueError: Input 0 is incompatible with layer model_7: expected shape=(None, 784), found shape=(32, 28, 28)

代码：-

#Encoder
input1 = Input(shape = (784,))
hidden1 = Dense(128, activation = 'relu')(input1)
hidden2 = Dense(64, activation = 'relu')(hidden1)
hidden3 = Dense(32, activation = 'relu')(hidden2)
model = Model(inputs = input1, outputs = hidden3)

模型总结：

Model: "model_7"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_17 (InputLayer)        [(None, 784)]             0         
_________________________________________________________________
dense_43 (Dense)             (None, 128)               100480    
_________________________________________________________________
dense_44 (Dense)             (None, 64)                8256      
_________________________________________________________________
dense_45 (Dense)             (None, 32)                2080      
=================================================================
Total params: 110,816
Trainable params: 110,816
Non-trainable params: 0

---

拟合模型后的错误：-

Epoch 1/3
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-42-3295f6ac1688> in <module>
----> 1 model.fit(x_train, y_train, epochs = 3)

C:\Anaconda\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)
   1098                 _r=1):
   1099               callbacks.on_train_batch_begin(step)
-> 1100               tmp_logs = self.train_function(iterator)
   1101               if data_handler.should_sync:
   1102                 context.async_wait()

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    826     tracing_count = self.experimental_get_tracing_count()
    827     with trace.Trace(self._name) as tm:
--> 828       result = self._call(*args, **kwds)
    829       compiler = "xla" if self._experimental_compile else "nonXla"
    830       new_tracing_count = self.experimental_get_tracing_count()

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    869       # This is the first call of __call__, so we have to initialize.
    870       initializers = []
--> 871       self._initialize(args, kwds, add_initializers_to=initializers)
    872     finally:
    873       # At this point we know that the initialization is complete (or less

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
    723     self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
    724     self._concrete_stateful_fn = (
--> 725         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
    726             *args, **kwds))
    727 

C:\Anaconda\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2967       args, kwargs = None, None
   2968     with self._lock:
-> 2969       graph_function, _ = self._maybe_define_function(args, kwargs)
   2970     return graph_function
   2971 

C:\Anaconda\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3359 
   3360           self._function_cache.missed.add(call_context_key)
-> 3361           graph_function = self._create_graph_function(args, kwargs)
   3362           self._function_cache.primary[cache_key] = graph_function
   3363 

C:\Anaconda\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3194     arg_names = base_arg_names + missing_arg_names
   3195     graph_function = ConcreteFunction(
-> 3196         func_graph_module.func_graph_from_py_func(
   3197             self._name,
   3198             self._python_function,

C:\Anaconda\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)
    988         _, original_func = tf_decorator.unwrap(python_func)
    989 
--> 990       func_outputs = python_func(*func_args, **func_kwargs)
    991 
    992       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    632             xla_context.Exit()
    633         else:
--> 634           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    635         return out
    636 

C:\Anaconda\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    975           except Exception as e:  # pylint:disable=broad-except
    976             if hasattr(e, "ag_error_metadata"):
--> 977               raise e.ag_error_metadata.to_exception(e)
    978             else:
    979               raise

ValueError: in user code:

    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:805 train_function  *
        return step_function(self, iterator)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    C:\Anaconda\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    C:\Anaconda\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    C:\Anaconda\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:788 run_step  **
        outputs = model.train_step(data)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:754 train_step
        y_pred = self(x, training=True)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:998 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:271 assert_input_compatibility
        raise ValueError('Input ' + str(input_index) +

    ValueError: Input 0 is incompatible with layer model_7: expected shape=(None, 784), found shape=(32, 28, 28)

这个错误是什么意思，我需要改变输入维度吗？如果是，那么我的输入维度是多少？

火车的形状和测试数据- 提前问好。

Answer 1

您的输入图像是 28 x 28 图像，需要转换为包含 784 个值的向量。虽然有多种方法可以做到这一点，但最简单的方法是使用 Keras 提供的Flatten 层。在这种情况下，您对模型的输入将是 28 x 28 图像：

input1 = Input(shape = (28, 28))
flattened_input = Flatten()(input1)
hidden1 = Dense(128, activation = 'relu')(flattened_input)
hidden2 = Dense(64, activation = 'relu')(hidden1)
hidden3 = Dense(32, activation = 'relu')(hidden2)
model = Model(inputs = input1, outputs = hidden3)