使用密集层创建 MLP 时出现“激活”的名称错误答案

【问题标题】：Name error of "activation" while creating a MLP using dense layers使用密集层创建 MLP 时出现“激活”的名称错误
【发布时间】：2020-05-23 02:48:29
【问题描述】：

NameError                                 Traceback (most recent call last)
<ipython-input-28-3f33c21e54b4> in <module>()
      1 num_of_features=x_train.shape[1]
      2 model=Sequential()
----> 3 model.add(Dense(20, activation=="relu",kernel_initializer='he_normal',input_shape=(num_of_features,)))
      4 model.add(Dense(10, activation=="relu",kernel_initializer="he_normal"))
      5 model.add(Dense(5, activation="relu",kernel_initializer="he_normal"))

NameError: name 'activation' is not defined

这是我导入 Dense 和 tensorflow 的代码，我不明白为什么会出现上述错误

import tensorflow as tf
from pandas import read_csv
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from tensorflow.keras.layers import Dense
from tensorflow.keras import Sequential

num_of_features=x_train.shape[1]
model=Sequential()
model.add(Dense(20, activation=="relu",kernel_initializer='he_normal',input_shape=(num_of_features,)))
model.add(Dense(10, activation=="relu",kernel_initializer="he_normal"))
model.add(Dense(5, activation="relu",kernel_initializer="he_normal"))
model.add(Dense(1, activation="sigmoid"))

【问题讨论】：

标签： python tensorflow tf.keras

【解决方案1】：

您只需在Dense 层的参数中输入一个=。将您的代码更改为

import tensorflow as tf
from pandas import read_csv
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from tensorflow.keras.layers import Dense
from tensorflow.keras import Sequential
num_of_features=x_train.shape[1]
model=Sequential()
model.add(Dense(20, activation="relu",kernel_initializer='he_normal',input_shape=(num_of_features,)))
model.add(Dense(10, activation="relu",kernel_initializer="he_normal"))
model.add(Dense(5, activation="relu",kernel_initializer="he_normal"))
model.add(Dense(1, activation="sigmoid"))

【讨论】：