Python-Keras:LSTM数据结构ValueError [英] Python - Keras: LSTM data structure ValueError

问题描述

我正在尝试使用return_sequence训练LSTM模型以返回每个输入时间步长的隐藏状态输出，以解决回归问题.

I'm trying to train an LSTM model using return_sequence to return the hidden state output for each input time step, solving a regression problem.

我的数据形状为:(31、2720、16)，即31批具有16个特征的2720个样本.
我的目标形状是:(31，2720，1)，即31批2720行包含1个值.

My Data shape is: (31, 2720, 16) i.e 31 batches of 2720 samples with 16 features.
My target shape is: (31, 2720, 1) i.e 31 batches of 2720 rows containing 1 value.

我建立了以下模型:

model = Sequential()
opt = Adam(learning_rate=0.0001, clipnorm=1)

num_samples = train_x.shape[1]
num_features = train_x.shape[2]

model.add(Masking(mask_value=-10., input_shape=(num_samples, num_features)))


model.add(LSTM(32, return_sequences=True, stateful=False, activation='tanh'))
model.add(Dropout(0.3))

#this is the last LSTM layer, use return_sequences=False
model.add(LSTM(16, return_sequences=False, stateful=False,  activation='tanh'))
model.add(Dropout(0.3))
model.add(Dense(16, activation='tanh'))
model.add(Dense(8, activation='tanh'))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='mse', optimizer='adam' ,metrics=[metrics.mean_absolute_error, metrics.mean_squared_error])

logdir = os.path.join(logs_base_dir, datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
tensorboard_callback = TensorBoard(log_dir=logdir, update_freq=1)
model.summary()

摘要:

Model: "sequential_33"

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
masking_24 (Masking)         (None, 2720, 16)          0         
_________________________________________________________________
lstm_61 (LSTM)               (None, 2720, 32)          6272      
_________________________________________________________________
dropout_51 (Dropout)         (None, 2720, 32)          0         
_________________________________________________________________
lstm_62 (LSTM)               (None, 16)                3136      
_________________________________________________________________
dropout_52 (Dropout)         (None, 16)                0         
_________________________________________________________________
dense_67 (Dense)             (None, 16)                272       
_________________________________________________________________
dense_68 (Dense)             (None, 8)                 136       
_________________________________________________________________
dense_69 (Dense)             (None, 1)                 9         
=================================================================
Total params: 9,825
Trainable params: 9,825
Non-trainable params: 0
_________________________________________________________________

尝试拟合模型时，出现以下错误:

When trying to fit the model, I get the following error:

ValueError                                Traceback (most recent call last)
<ipython-input-354-afdba8dea179> in <module>()
----> 1 model.fit(train_x, train_y, epochs=1000, batch_size=128,validation_split = 0.2, callbacks=[tensorboard_callback,checkpoint])

5 frames
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training_utils.py in check_loss_and_target_compatibility(targets, loss_fns, output_shapes)
    808           raise ValueError('A target array with shape ' + str(y.shape) +
    809                            ' was passed for an output of shape ' + str(shape) +
--> 810                            ' while using as loss `' + loss_name + '`. '
    811                            'This loss expects targets to have the same shape '
    812                            'as the output.')

我正在尝试掌握正确的数据结构方式，我想念的是什么?

I'm trying to grasp the right way to structure the data, what am I missing?

推荐答案

您的目标的形状为(31, 2720, 1)，当前模型的输出结果的形状为(31, 1).这种情况下的错误是自我解释.

Your target is of shape (31, 2720, 1) and the output of your current model will be of shape (31, 1). The error in this case is self explainatory.

您可以通过以下两种方式之一解决此问题:

You can solve this in one of two ways:

1. 查看您的模型，我猜您只希望相对于最后一个序列损失.在这种情况下，您可以按以下方式调用model.fit:

model.fit(train_x, train_y[:, -1, :], ...) 

如果要计算所有时间步长的损耗，请将return_sequences=True添加到第二个LSTM层:

If you want to compute the loss across all timesteps, add return_sequences=True to the second LSTM layer:

model.add(LSTM(16, return_sequences=True, stateful=False,  activation='tanh'))

这篇关于Python-Keras:LSTM数据结构ValueError的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！