ValueError：检查输入时出错：预期 lstm_16_input 有 3 个维度，但得到的数组形状为 (836, 400, 3, 1)

Posted 2023-03-12

【中文标题】ValueError：检查输入时出错：预期 lstm_16_input 有 3 个维度，但得到的数组形状为 (836, 400, 3, 1)

【英文标题】：ValueError: Error when checking input: expected lstm_16_input to have 3 dimensions, but got array with shape (836, 400, 3, 1)

【发布时间】：2020-07-27 16:18:21

【问题描述】：

我的输入是一个 CSV 文件，我制作了大约 400 个样本的片段。特征是 3 (x, y,z)。首先，我使用model.add(Conv2D(16, (2, 2), activation = 'relu', input_shape = x_train[0].shape)) 应用CNN2D。它确实有效，但是在 LSTM 的情况下，输入显示错误。因此，我将输入更改为model.add(LSTM(32, input_shape = (400,3), return_sequences=True))，然后这段代码有效，但在 model.fit 下面我遇到了问题。请在下面找到代码和错误：

x_train.shape, x_test.shape 

上述代码的输出： ((836, 400, 3), (209, 400, 3))

x_train = x_train.reshape(836, 400, 3, 1)   
x_test = x_test.reshape(209, 400, 3, 1)

x_train[0].shape  #output of this line: (400, 3, 1)


model = Sequential()     
model.add(LSTM(32, input_shape = (400,3), return_sequences=True))

model.add(Dropout(0.5)) 
model.add(Dense(100, activation='relu')) 
model.add(Flatten())
#Then Here we have Dense Layer 
model.add(Dense(64, activation= 'relu')) 
model.add(Dropout(0.5)) 
model.add(Dense(3, activation='softmax'))
model.compile(optimizer=Adam(learning_rate = 0.001), loss = 'sparse_categorical_crossentropy', metrics=['accuracy'])
history = model.fit(x_train, y_train, epochs = 10, validation_data = (x_test, y_test), verbose=1) 

错误

    ---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-109-3ffd974b58e0> in <module>
      1 #Record this model tranning into a history
      2 
----> 3 history = model.fit(x_train, y_train, epochs = 10, validation_data = (x_test, y_test), verbose=1)
      4 #Below here you can see xthe training, here at the very first step 75% traning accuracy and 84% validation accuracy, After 10
      5 #epoc you see 91% of traning accuracy and 87% validaton accuracy, (As a complement, with accelrometer data, this is very good

c:\users\nafee\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
    726         max_queue_size=max_queue_size,
    727         workers=workers,
--> 728         use_multiprocessing=use_multiprocessing)
    729 
    730   def evaluate(self,

c:\users\nafee\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, **kwargs)
    222           validation_data=validation_data,
    223           validation_steps=validation_steps,
--> 224           distribution_strategy=strategy)
    225 
    226       total_samples = _get_total_number_of_samples(training_data_adapter)

c:\users\nafee\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in _process_training_inputs(model, x, y, batch_size, epochs, sample_weights, class_weights, steps_per_epoch, validation_split, validation_data, validation_steps, shuffle, distribution_strategy, max_queue_size, workers, use_multiprocessing)
    545         max_queue_size=max_queue_size,
    546         workers=workers,
--> 547         use_multiprocessing=use_multiprocessing)
    548     val_adapter = None
    549     if validation_data:

c:\users\nafee\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in _process_inputs(model, x, y, batch_size, epochs, sample_weights, class_weights, shuffle, steps, distribution_strategy, max_queue_size, workers, use_multiprocessing)
    592         batch_size=batch_size,
    593         check_steps=False,
--> 594         steps=steps)
    595   adapter = adapter_cls(
    596       x,

c:\users\nafee\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split, shuffle, extract_tensors_from_dataset)
   2470           feed_input_shapes,
   2471           check_batch_axis=False,  # Don't enforce the batch size.
-> 2472           exception_prefix='input')
   2473 
   2474     # Get typespecs for the input data and sanitize it if necessary.

c:\users\nafee\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    563                            ': expected ' + names[i] + ' to have ' +
    564                            str(len(shape)) + ' dimensions, but got array '
--> 565                            'with shape ' + str(data_shape))
    566         if not check_batch_axis:
    567           data_shape = data_shape[1:]

ValueError: Error when checking input: expected lstm_16_input to have 3 dimensions, but got array with shape (836, 400, 3, 1)

有解决这个问题的办法吗？

【问题讨论】：

这些是否相关？ ***.com/questions/44704435/…stats.stackexchange.com/questions/370186/…

@SteveK 感谢您的反馈。我已经检查了这个链接，但从我的数据的角度来看无法理解。请您根据我的代码在这里尝试一下。谢谢

【参考方案1】：

LSTM 的输入形状是batch_size X time_steps X input_size（当批量优先时）。即，LSTM/循环网络对每个样本展开time_steps 次，每次展开都会得到input_size 的输入。

以免看到你的模型架构：

Layer (type)                 Output Shape              Param #   
=================================================================
lstm_3 (LSTM)                (None, 400, 32)           4608      
_________________________________________________________________
dropout_5 (Dropout)          (None, 400, 32)           0         
_________________________________________________________________
dense_7 (Dense)              (None, 400, 100)          3300      
_________________________________________________________________
flatten_3 (Flatten)          (None, 40000)             0         
_________________________________________________________________
dense_8 (Dense)              (None, 64)                2560064   
_________________________________________________________________
dropout_6 (Dropout)          (None, 64)                0         
_________________________________________________________________
dense_9 (Dense)              (None, 3)                 195       
=================================================================
Total params: 2,568,167
Trainable params: 2,568,167
Non-trainable params: 0

LSTM的输入大小是batch_size X 400 X 3，输出大小是``batch_size X 400 X 32(since return_sequence is true). so you will have to pass your836train samples of400length and each having 3 features(x,y,z)`到lstm。您可以通过挤出最后一个维度来重塑您的输入。

代码

from keras.layers import Dropout, Flatten, Dense, LSTM
from keras.models import Sequential
from keras.optimizers import Adam

x_train = np.random.randn(836, 400, 3, 1).squeeze() # This will reshape to (836, 400, 3)
x_test  = np.random.randn(209, 400, 3, 1).squeeze() # This will reshape to (209, 400, 3)

y_train = np.random.randint(0,3,size=(836))
y_test = np.random.randint(0,3,size=(209))

model = Sequential()     
model.add(LSTM(32, input_shape = (400,3), return_sequences=True))

model.add(Dropout(0.5)) 
model.add(Dense(100, activation='relu')) 
model.add(Flatten())
#Then Here we have Dense Layer 
model.add(Dense(64, activation= 'relu')) 
model.add(Dropout(0.5)) 
model.add(Dense(3, activation='softmax'))

model.compile(optimizer=Adam(learning_rate = 0.001), loss = 'sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs = 2, verbose=1, validation_data = (x_test, y_test)) 

输出

Train on 836 samples, validate on 209 samples
Epoch 1/2
836/836 [==============================] - 6s 7ms/step - loss: 1.1725 - accuracy: 0.3469 - val_loss: 1.0996 - val_accuracy: 0.3301
Epoch 2/2
836/836 [==============================] - 5s 6ms/step - loss: 1.0893 - accuracy: 0.3947 - val_loss: 1.1026 - val_accuracy: 0.2727

【讨论】：

它运行良好。太感谢了。但是，我在使用 CNN 方面处于初级水平。因此，我无法完全了解模型架构，特别是关于参数计算？你能解释一下吗？此外，在输出形状中，“无”表示什么？

您基本上从基于问题复杂性的 VGG、Resnet 等众所周知的架构开始。超参数调优大多是经验问题，尝试不同的参数。None（第一维）表示batch size。