使用input_shape=(30,2)时，您要使用3个维度定义输入:(batchSize, 30, 2).

可以，但是可以不更改地传递到模型中，直到到达密集层为止.

密集层不会减少尺寸数量，它们将输出(batchSize, 30, denseUnits).

一种解决方案是使用平坦层，将其减少到仅(batchSize,30*someValue).然后密集对象将开始输出(batchSize,units).这将为您提供与您的2D类匹配的2D输出.

在密集层之前:

model.add(Flatten())

I have a time series (2 variables), each time series has about 80000 observations (X), each observation corresponds to a class (Y). I used moving window method to segment the time series to several intervals (each has a length of 30). Then I hot encoded the Y to make it to categorical variable.

---

Then I created batches with batch size of 64 with the following code

from sklearn.preprocessing import OneHotEncoder

def one_hot_encoder(y):

    onehot_encoder = OneHotEncoder(sparse=False)
    y = y.reshape(len(y), 1)
    onehot_encoder = onehot_encoder.fit_transform(y)
    return onehot_encoder

def data_generator(x, y, shuffle=False, batch_size=64):

    # create order
    while True:
        index = np.arange(len(y))
        if shuffle == True:
            np.random.shuffle(index)
            x = x[index]
            y = y[index]

        # generate batches
        imax = int(len(index)/batch_size)
        for i in range(imax):
            yield x[i*batch_size: (i+1)*batch_size], y[i*batch_size: (i+1)*batch_size]


def get_batches(x, y):

    x = np.array(x)
    y = np.array(y)

    return data_generator(x, one_hot_encoder(y))

---

For each batch print(next(batches)[0].shape) is (64, 30 ,2) -- 30 observations, 2 variables print(next(batches)1.shape) is (64, 3) - each observation corresponds to a hot-encoded class

---

Then I create Model with the following code:

def create_model():
    model = Sequential()
    model.add(BatchNormalization(axis=1, input_shape=(30, 2)))
    model.add(Conv1D(16, 5, activation='relu'))
    model.add(BatchNormalization(axis=1))
    model.add(MaxPooling1D(2))
    model.add(Conv1D(16, 5, activation='relu'))
    model.add(BatchNormalization(axis=1))
    model.add(MaxPooling1D(3))
    model.add(Conv1D(32, 3, activation='relu'))
    model.add(Dense(100, activation='relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.5))
    model.add(Dense(3, activation='softmax'))

    return model

model = create_model()
model.compile(RMSprop(lr=0.01), loss='categorical_crossentropy', metrics=['accuracy'])

The summary of the model is as follow:

model summary

But when I train the model using fit_generator, I get the following error message. I am really confused whether my output dimension is not correct? or is there any error in my code.

Thanks.

model.fit_generator(batches, steps_per_epoch=30, nb_epoch=5, validation_data=None, validation_steps=None)

---

ValueError                                Traceback (most recent call last)
<ipython-input-29-c7ba2e8eddfd> in <module>()
----> 1 model.fit_generator(batches, steps_per_epoch=10, nb_epoch=5, validation_data=None, validation_steps=None)

D:\Programs\Anaconda3\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
     85                 warnings.warn('Update your `' + object_name +
     86                               '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 87             return func(*args, **kwargs)
     88         wrapper._original_function = func
     89         return wrapper

D:\Programs\Anaconda3\lib\site-packages\keras\models.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, initial_epoch)
   1119                                         workers=workers,
   1120                                         use_multiprocessing=use_multiprocessing,
-> 1121                                         initial_epoch=initial_epoch)
   1122 
   1123     @interfaces.legacy_generator_methods_support

D:\Programs\Anaconda3\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
     85                 warnings.warn('Update your `' + object_name +
     86                               '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 87             return func(*args, **kwargs)
     88         wrapper._original_function = func
     89         return wrapper

D:\Programs\Anaconda3\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
   2040                     outs = self.train_on_batch(x, y,
   2041                                                sample_weight=sample_weight,
-> 2042                                                class_weight=class_weight)
   2043 
   2044                     if not isinstance(outs, list):

D:\Programs\Anaconda3\lib\site-packages\keras\engine\training.py in train_on_batch(self, x, y, sample_weight, class_weight)
   1754             sample_weight=sample_weight,
   1755             class_weight=class_weight,
-> 1756             check_batch_axis=True)
   1757         if self.uses_learning_phase and not isinstance(K.learning_phase(), int):
   1758             ins = x + y + sample_weights + [1.]

D:\Programs\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size)
   1380                                     output_shapes,
   1381                                     check_batch_axis=False,
-> 1382                                     exception_prefix='target')
   1383         sample_weights = _standardize_sample_weights(sample_weight,
   1384                                                      self._feed_output_names)

D:\Programs\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    130                                  ' to have ' + str(len(shapes[i])) +
    131                                  ' dimensions, but got array with shape ' +
--> 132                                  str(array.shape))
    133             for j, (dim, ref_dim) in enumerate(zip(array.shape, shapes[i])):
    134                 if not j and not check_batch_axis:

ValueError: Error when checking target: expected dense_2 to have 3 dimensions, but got array with shape (64, 3)

When you use input_shape=(30,2), you are defining your input with 3 dimensions: (batchSize, 30, 2).

This is ok, but it's being passed through your model unchanged until it reaches the dense layers.

Dense layers won't reduce the number of dimensions, they will output (batchSize, 30, denseUnits).

One solution is to use a flatten layer, to reduce to only (batchSize,30*someValue). Then the dense will start outputting (batchSize,units) This will provide you a 2D output that matches your 2D classes.

Before the dense layers:

model.add(Flatten())