Python 输入形状的Keras LSTM输入形状错误
我在使用Keras的时间序列时遇到以下错误:Python 输入形状的Keras LSTM输入形状错误,python,keras,keras-layer,Python,Keras,Keras Layer,我在使用Keras的时间序列时遇到以下错误: ValueError: Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (31, 3) 这是我的职责: def CreateModel(shape): """Creates Keras Model. Args: shape: (set) Dataset shape. Example: (3
ValueError: Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (31, 3)
这是我的职责:
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
主要代码:
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)
完全错误:
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)
但我得到:
ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4
如果你的原始数据是(31,3),那么我认为你要找的是一个训练。你可以通过下面的一行得到
training\u features=training\u features.重塑(-1,3,1)
这将简单地向现有数据添加一个新的轴(1只是告诉numpy使用原始数据中的值来计算这个维度)
您还需要修复模型的输入形状。31应该是数据中的样本数。这不包括在Kerasinput\u shape
参数中。你应该使用
model.add(LSTM(4,input_-shape=(3,1)))
Keras将自动将批次大小设置为None
,这意味着任何数量的样本都将与模型一起工作
ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4