python 中的神经元网络错误：预期具有形状 (...) 但得到的数组具有形状 (...)

Question

from keras.models import Sequential
from keras.layers import Dense
import pandas as pd
import numpy as np

data = pd.read_csv('D:Python\diabetes.csv')
data.columns ['n_embarazo', 'glucosa_concentracion', 'PA_diastolica', 'grosor_triceps', 'insulina_serica', 'IMC', 'pedigri_diabetes', 'edad', 'aparicion']
df = pd.DataFrame(data)
x = df.iloc[:,0:8].values
y = df.iloc[:,8].values

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.20)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()

x_train = sc.fit_transform(x_train)
x_test = sc.fit_transform(x_test)

from keras import Sequential
from keras.layers import Dense

cf = Sequential()
cf.add(Dense(units=12,kernel_initializer='uniform',activation='relu',input_dim=11))
cf.add(Dense(units=12,kernel_initializer='uniform',activation='relu'))
cf.add(Dense(units=1,kernel_initializer='uniform',activation='sigmoid'))
cf.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
cf.fit(x_train,y_train,batch_size=10,epochs=100)

检查输入时出错：预期 dense_13_input 的形状为 (11,) 但得到的数组的形状为 (8,)

Answer 1

是写在错误里的，可以试试把 input_dim=11 改成 input_dim=8

cf.add(Dense(units=12,kernel_initializer='uniform',activation='relu',input_dim=8))

原因是您的 x_train 数据具有形状：something, 8