ValueError：检查输入时出错：预期dense_1_input具有形状（13，）但得到形状为（3，）的数组？

Question

我只是通过观看 YouTube 上的视频为葡萄酒数据创建神经网络，但我在 model.fit 中遇到错误

我是机器学习的新手，所以我不知道任何类型的解决方案，所以我没有尝试过任何东西。

from sklearn.model_selection import train_test_split
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout
import pandas as pd
import numpy as np
from google.colab import files

np.random.seed(3)

# Number of Wine Classes
classifications = 3

#load dataset
uploaded = files.upload() 


for fn in uploaded.keys():
  print('User uploaded file "{name}" with length {length} bytes'.format(
      name=fn, length=len(uploaded[fn])))

import io

dataset = pd.read_csv(io.StringIO(uploaded['wine.csv'].decode('utf-8')))

X = dataset[['Wine','Alcohol','Malic.acid','Ash','Acl','Mg','Phenols','Flavanoids','Nonflavanoid.phenols','Proanth','Color.int','Hue','OD','Proline']]

y = dataset[['Wine']]

# convert output values to one-hot
x_train = keras.utils.to_categorical(y_train-1, classifications)
x_test = keras.utils.to_categorical(y_test-1, classifications)

# creating model
model = Sequential()
model.add(Dense(10, input_dim=13, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(6, activation='relu'))
model.add(Dense(6, activation='relu'))
model.add(Dense(4, activation='relu'))
model.add(Dense(2, activation='relu'))
model.add(Dense(classifications, activation='softmax'))

# compile 
model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=['accuracy'])

# fit model
model.fit(x_train, y_train, batch_size=15, epochs=2500, validation_data=(x_test, y_test))

错误

ValueError：检查输入时出错：预期dense_1_input 的形状为(13，)，但得到的数组的形状为(3，)

Answer 1

在这里，你是 one_hot 编码输入值，而不是输出

# convert output values to one-hot
x_train = keras.utils.to_categorical(y_train-1, classifications)
x_test = keras.utils.to_categorical(y_test-1, classifications)

应该是：

# convert output values to one-hot
y_train = keras.utils.to_categorical(y_train-1, classifications)
y_test = keras.utils.to_categorical(y_test-1, classifications)

那么你只需要在 X 中保存特征而不是目标，所以你的新 X 是：

X = dataset[['Alcohol','Malic.acid','Ash','Acl','Mg','Phenols','Flavanoids','Nonflavanoid.phenols','Proanth','Color.int','Hue','OD','Proline']]

最后不要忘记在 fit 方法中更改变量：

model.fit(X_train, y_train, batch_size=25, epochs=5000, validation_data=(X_test, y_test))