python - LSTM 网络期望最后一层的目标具有 2 维，但得到形状为 (996, 1, 1) 的数组

Question

我尝试使用 TensorFlow 后端在玩具数据上通过 keras 训练 LSTM，但收到此错误:

ValueError: Error when checking target: expected dense_39 to have 2 dimensions, but got array with shape (996, 1, 1)

调用model.fit后立即发生错误；似乎没有什么运行。在我看来，Keras 正在检查尺寸，但忽略了这样一个事实:它应该在每批输入中获取我的目标批处理。该错误显示了我的目标数组的完整维度，这对我来说意味着它永远不会被 Keras 分成批处理，至少在检查维度时是这样。对于我的一生，我无法弄清楚为什么会这样或任何其他可能有帮助的事情。

我的网络定义以及注释中的预期层输出形状:

batch_shape = (8, 5, 1)
x_in = Input(batch_shape=batch_shape, name='input')  # (8, 5, 1)
seq1 = LSTM(8, return_sequences=True, stateful=True)(x_in)  # (8, 5, 8)
dense1 = TimeDistributed(Dense(8))(seq1)  # (8, 5, 8)
seq2 = LSTM(8, return_sequences=False, stateful=True)(dense1)  # (8, 8)
dense2 = Dense(8)(seq2)  # (8, 8)
out = Dense(1)(dense2)  # (8, 1)

model = Model(inputs=x_in, outputs=out)
optimizer = Nadam()
model.compile(optimizer=optimizer, loss='mean_squared_error')
model.summary()

模型摘要，形状符合预期:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input (InputLayer)           (8, 5, 1)                 0         
_________________________________________________________________
lstm_28 (LSTM)               (8, 5, 8)                 320       
_________________________________________________________________
time_distributed_18 (TimeDis (8, 5, 8)                 72        
_________________________________________________________________
lstm_29 (LSTM)               (8, 8)                    544       
_________________________________________________________________
dense_38 (Dense)             (8, 8)                    72        
_________________________________________________________________
dense_39 (Dense)             (8, 1)                    9         
=================================================================
Total params: 1,017
Trainable params: 1,017
Non-trainable params: 0
_________________________________________________________________

我的玩具数据，其中目标只是从 100 到 0 递减的一条线，输入只是一个零数组。我想要进行一步预测，因此我使用下面定义的 rolling_window() 方法创建输入和目标的滚动窗口:

target = np.linspace(100, 0, num=1000)
target_rolling = rolling_window(target[4:], 1)[:, :, None]
target_rolling.shape  # (996, 1, 1)  <-- this seems to be the array that's causing the error
x_train = np.zeros((1000,))
x_train_rolling = rolling_window(x_train, 5)[:, :, None]
x_train_rolling.shape  # (996, 5, 1)

rolling_window() 方法:

def rolling_window(arr, window):
    shape = arr.shape[:-1] + (arr.shape[-1] - window + 1, window)
    strides = arr.strides + (arr.strides[-1],)
    return np.lib.stride_tricks.as_strided(arr, shape=shape, strides=strides)

我的训练循环:

reset_state = LambdaCallback(on_epoch_end=lambda _, _: model.reset_states())
callbacks = [reset_state]
history = model.fit(x_train_rolling, y_train_rolling,
                    batch_size=8,
                    epochs=100,
                    validation_split=0.,
                    callbacks=callbacks)

我已经尝试过:

• 无状态 LSTM，但我确实需要有状态的最终应用程序。同样的错误。
• return_sequence=True 在第二个 LSTM 中，后面有一个 Flatten 层。同样的错误。
• return_sequence=True 没有Flatten层。这会产生不同的错误，因为它期望目标具有与输出相同的形状，此时为 (batch_size, 5, 1) 而不是 (batch_size, 1, 1) 。
• 一次在整个序列上运行相同的架构(批量大小为 1)，无需滚动窗口。这可行，但只是学习近似我的目标的平均值，对我的目的来说毫无用处。

请注意，这些问题似乎都不能直接回答我的问题，尽管我对其中几个问题确实充满希望:

• Error when checking target: expected time_distributed_5 to have 3 dimensions, but got array with shape (14724, 1)
• LSTM and CNN: ValueError: Error when checking target: expected time_distributed_1 to have 3 dimensions, but got array with shape (400, 256)
• ValueError: Error when checking target: expected lstm_27 to have 2 dimensions, but got array with shape (1, 11, 1)
• expected dense_218_input to have 2 dimensions, but got array with shape (512, 28, 28, 1)
• expected dense_1 to have 2 dimensions, but got array with shape (308, 1, 6)

Answer 1

发布我在评论中写的解决方案: 由于存在额外尺寸，“-1”使尺寸自行调整为适合其他尺寸的任何数字。由于只给出了两个维度，“(-1,1)”将使其变为“(996, 1)”。

target_rolling = target_rolling.reshape(-1,1)

之前

at target_rolling.shape # (996, 1, 1)