Machine learning 在python中添加输出层的困难

当我尝试运行代码时，出现以下错误：

  File "C:\Users\olaku\anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)

TypeError: __init__() missing 1 required positional argument: 'units'".

我的代码：

# Importing the relevant libraries.
import numpy as np
import pandas as pd


#importing the dataset
dataset = pd.read_csv ('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X_1 = LabelEncoder()
X[:, 1] = labelencoder_X_1.fit_transform(X[:, 1])
labelencoder_X_2 = LabelEncoder()
X[:, 2] = labelencoder_X_2.fit_transform(X[:, 2])
onehotencoder = OneHotEncoder(categories='auto', drop=None, sparse=True)
X = onehotencoder.fit_transform(X).toarray()
X = X[:, 1:]

# Splitting the dataset into training and testing set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 123)

#Feature Scalling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# Part 2: Make the Artifical Neural Network (ANN)

#Import the Keras library and packages
import keras
from keras.models import Sequential
from keras.layers import Dense


#Initialising the ANN

classifier = Sequential ()

classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu', input_dim = 11))

#Adding the second hidden layer
classifier.add(Dense(units = 6, kernel_initializer = 'uniform', activation = 'relu'))

#Adding the output layer

classifier.add(Dense(output = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))

尝试以下更改：

classifier.add(Dense(6, kernel_initializer = 'uniform', activation = 'relu', input_dim = 11))

#Adding the second hidden layer
classifier.add(Dense(6, kernel_initializer = 'uniform', activation = 'relu'))

#Adding the output layer

classifier.add(Dense(1, kernel_initializer = 'uniform', activation = 'sigmoid'))

---

让我知道

请编辑您的问题以包含完整的错误跟踪；实际上，不可能知道错误发生在代码中的确切位置。完成后，请确保删除错误后的所有代码（它从未执行，因此与此处无关）。今后，还要确保您已经包含了相关的标签（这里是

keras

和

scikit-learn

）。