[英]Keras LSTM input shape error for input shape
將時間序列與Keras結合使用時出現此錯誤:
ValueError: Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (31, 3)
這是我的功能:
def CreateModel(shape):
"""Creates Keras Model.
Args:
shape: (set) Dataset shape. Example: (31,3).
Returns:
A Keras Model.
Raises:
ValueError: Invalid shape
"""
if not shape:
raise ValueError('Invalid shape')
logging.info('Creating model')
model = Sequential()
model.add(LSTM(4, input_shape=(31, 3)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
return model
主要代碼:
print(training_features.shape)
model = CreateModel(training_features.shape)
model.fit(
training_features,
training_label,
epochs=FLAGS.epochs,
batch_size=FLAGS.batch_size,
verbose=FLAGS.keras_verbose_level)
完成錯誤:
Traceback (most recent call last):
File "<embedded module '_launcher'>", line 149, in run_filename_as_main
File "<embedded module '_launcher'>", line 33, in _run_code_in_main
File "model.py", line 300, in <module>
app.run(main)
File "absl/app.py", line 433, in run
_run_main(main, argv)
File "absl/app.py", line 380, in _run_main
sys.exit(main(argv))
File "model.py", line 274, in main
verbose=FLAGS.keras_verbose_level)
File "keras/models.py", line 960, in fit
validation_steps=validation_steps)
File "keras/engine/training.py", line 1581, in fit
batch_size=batch_size)
File "keras/engine/training.py", line 1414, in _standardize_user_data
exception_prefix='input')
File "keras/engine/training.py", line 141, in _standardize_input_data
str(array.shape))
ValueError: Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (31, 3)
最初來自這里的代碼
我努力了:
training_features = numpy.reshape(
training_features,
(training_features.shape[0], 1, training_features.shape[1]))
但是我得到:
ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4
如果您的原始數據是(31,3),那么我認為您正在尋找的是training_features.shape =(31,3,1)。 您可以通過以下行來獲取...
training_features = training_features.reshape(-1, 3, 1)
這將僅向現有數據添加一個新軸(-1只是告訴numpy使用原始數據中的值來確定該維)。
您還需要修復模型的輸入形狀。 31應該是您數據中的樣本數。 這不會包含在input_shape
參數中。 您應該使用...
model.add(LSTM(4, input_shape=(3, 1)))
Keras會自動將批次大小設置為“ None
這意味着該模型可以使用任何數量的樣本。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.