我在使用Keras模型时遇到了一个问题。代码如下：

首先，这是输入数据，X是图像，之后会显示它们的维度

print(len(X), len(target))1500 1500

X = np.array(X, dtype="float") / 255.0target = to_categorical(target,10)target = np.array(target)X_train, X_test, y_train, y_test = train_test_split(X,                                                    target,                                                    test_size = 0.2,                                                    random_state = 777)X_train, X_val, y_train, y_val = train_test_split(X_train,                                                  y_train,                                                  test_size = 0.4,                                                  random_state = 777)

然后我展示了三个数据集的所有维度：

print("x_train shape = ", X_train.shape)print("y_train shape = ", y_train.shape)print("\nx_validation shape = ", X_val.shape)print("y_validation shape = ", y_val.shape)print("\nx_test shape = ", X_test.shape)print("y_test shape = ", y_test.shape)x_train shape =  (720, 150, 150, 3)y_train shape =  (720, 10)x_validation shape =  (480, 150, 150, 3)y_validation shape =  (480, 10)x_test shape =  (300, 150, 150, 3)y_test shape =  (300, 10)

从这里我们可以看出这些维度看起来是正常的

model=Sequential()model.add(Conv2D(filters=96,kernel_size=(11,11),strides=(4,4),padding="valid",activation="relu",input_shape=(150,150,3)))model.add(MaxPooling2D(pool_size=(3,3),strides=(2,2)))model.add(BatchNormalization())model.add(Conv2D(filters=256,kernel_size=(5,5),strides=(1,1),padding="valid",activation="relu"))model.add(MaxPooling2D(pool_size=(3,3),strides=(2,2)))model.add(BatchNormalization())model.add(Conv2D(filters=384,kernel_size=(3,3),strides=(1,1),padding="valid",activation="relu"))model.add(Conv2D(filters=384,kernel_size=(3,3),strides=(1,1),padding="valid",activation="relu"))model.add(Dense(4096,input_shape=(227,227,3),activation="relu"))model.add(Dropout(0.4))model.add(BatchNormalization())model.add(Dense(4096,activation="relu"))model.add(Dropout(0.4))model.add(BatchNormalization())model.add(Dense(1000,activation="relu"))model.add(Dropout(0.4))model.add(BatchNormalization())model.add(Dense(10, activation="softmax"))

这是我的错误信息：

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])history = model.fit(X_train,                    y_train,                    epochs=30)

Epoch 1/30---------------------------------------------------------------------------ValueError                                Traceback (most recent call last)<ipython-input-61-95c7b541e6c9> in <module>()      4 history = model.fit(X_train,      5                     y_train,----> 6                     epochs=EPOCHS)9 frames/usr/local/lib/python3.6/dist-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               raiseValueError: in user code:    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function  *        return step_function(self, iterator)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function  **        outputs = model.distribute_strategy.run(run_step, args=(data,))    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica        return self._call_for_each_replica(fn, args, kwargs)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica        return fn(*args, **kwargs)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step  **        outputs = model.train_step(data)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:756 train_step        y, y_pred, sample_weight, regularization_losses=self.losses)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:203 __call__        loss_value = loss_obj(y_t, y_p, sample_weight=sw)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:152 __call__        losses = call_fn(y_true, y_pred)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:256 call  **        return ag_fn(y_true, y_pred, **self._fn_kwargs)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper        return target(*args, **kwargs)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1537 categorical_crossentropy        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper        return target(*args, **kwargs)    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4833 categorical_crossentropy        target.shape.assert_is_compatible_with(output.shape)    /usr/local/lib/python3.6/dist-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, 10) and (None, 2, 2, 10) are incompatible

我查看了关于这种错误的一些话题，但没有一个能精确地帮助我..

回答：

错误是因为你的输出形状与标签形状不同而引发的。

如你所提供的，标签形状是(None, 10)，这是正确的。

错误信息显示的输出形状是(None, 2, 2, 10)，这是不正确的。

你的输出形状错误的原因是在第一个Dense层之前和最后一个Conv2D层之后没有添加Flatten层来平展最后一个Conv2D层的输出。（关于如何实现Flatten层，请参考Keras文档，这很简单。）

你需要Flatten层的原因是Keras的Dense层不会自动将形状为（比如说）(10, 10, 30)的层平展为(10 * 10 * 30)。所以在最后一个Conv2D层之后，你的输出形状可能是(2, 2, 384)，经过第一个Dense层后会变成(2, 2, 4096)，经过最后一个Dense层后会变成(2, 2, 10)。换句话说，Keras的Dense层只会应用于它接收到的输入的最后一个维度。

一些相关点：

1. 你不需要为Dense层指定input_shape。

2. 对于所有这类形状相关的错误，使用model.summary()来检查你的模型是一个很好的方法，可以帮助你发现神经网络结构中的错误之处。