如何训练具有多维输入的 Keras LSTM？

Question

这是我输入数据的形状：

>> print(X_train.shape)
(1125, 75, 2)

然后我尝试通过这种方式构建模型：

model = Sequential()

model.add(LSTM(
    output_dim=50,
    input_shape = (75, 2),
    #input_shape = X_train.shape[1:],
    return_sequences=True))
model.add(Dropout(0.2))

model.add(LSTM(
    100,
    return_sequences=False))
model.add(Dropout(0.2))

model.add(Dense(
    output_dim=1))
model.add(Activation("linear"))

model.compile(loss="mse", optimizer="rmsprop")

model.fit(
    X_train,
    y_train,
    batch_size=512,
    nb_epoch=5,
    validation_split=0.1,
    verbose=0,
    shuffle=True)

但拟合时返回如下错误：

ValueError：检查模型目标时出错：预期激活_32 有 2 个维度，但得到了形状为 (1125, 75, 2) 的数组

这是完整的错误输出：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-48-b209fe29a91d> in <module>()
    152         verbose=0,
--> 153         shuffle=True)
    154 

/usr/local/lib/python3.5/dist-packages/keras/models.py in fit(self, x, y, batch_size, nb_epoch, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
    670                               class_weight=class_weight,
    671                               sample_weight=sample_weight,
--> 672                               initial_epoch=initial_epoch)
    673 
    674     def evaluate(self, x, y, batch_size=32, verbose=1,

/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in fit(self, x, y, batch_size, nb_epoch, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch)
   1114             class_weight=class_weight,
   1115             check_batch_axis=False,
-> 1116             batch_size=batch_size)
   1117         # prepare validation data
   1118         if validation_data:

/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size)
   1031                                    output_shapes,
   1032                                    check_batch_axis=False,
-> 1033                                    exception_prefix='model target')
   1034         sample_weights = standardize_sample_weights(sample_weight,
   1035                                                     self.output_names)

/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    110                                  ' to have ' + str(len(shapes[i])) +
    111                                  ' dimensions, but got array with shape ' +
--> 112                                  str(array.shape))
    113             for j, (dim, ref_dim) in enumerate(zip(array.shape, shapes[i])):
    114                 if not j and not check_batch_axis:

ValueError: Error when checking model target: expected activation_32 to have 2 dimensions, but got array with shape (1125, 75, 2)

我做错了什么？我关注了this tutorial of Keras documentation。

Answer 1

您的问题不在于输入形状，而在于输出形状。您需要重新检查您的y_train 是否具有适当的形状。