我正在尝试定义 LSTM 并收到错误“TypeError：add() 缺少 1 个必需的位置参数：'layer'”

Question

x_train.shape
    (1271, 322)
    x_scaler = MinMaxScaler()
    x_train = x_scaler.fit_transform(x_train)
    y_train.shape
    (1271, 161)
    y_scaler = MinMaxScaler()
    y_train = y_scaler.fit_transform(y_train)
    x_train = x_train.reshape(1271, 322, 1)
    reg = Sequential
    reg.add(LSTM(units = 200, activation = 'relu', input_shape = (322, 1)))
    reg.add(Dense(161))

TypeError                                 Traceback (most recent call last)
<ipython-input-43-ab4dcb49e16c> in <module>()
      1 reg = Sequential
----> 2 reg.add(LSTM(units = 200, activation = 'relu', input_shape = (322, 1)))
      3 reg.add(Dense(161))

/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
    455     self._self_setattr_tracking = False  # pylint: disable=protected-access
    456     try:
--> 457       result = method(self, *args, **kwargs)
    458     finally:
    459       self._self_setattr_tracking = previous_value  # pylint: disable=protected-access

TypeError: add() missing 1 required positional argument: 'layer'

Answer 1

这个模型定义对我来说效果很好：

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras import Sequential
from tensorflow.keras.layers import LSTM,Dense


reg = Sequential()
reg.add(LSTM(units = 200, activation = 'relu', input_shape = (322, 1))) 
reg.add(Dense(161))

还要检查你是否写了

reg = Sequential

，我认为应该是

reg = Sequential()