python - 分类神经网络模型未运行 : expected dense_84 to have shape

Question

我有大约 3600 行和 27 列的数据。其中一列中有一个从 1 到 10 的标签，我想根据其余列进行预测。

从头开始建模:

import tensorflow as tf
sess = tf.Session()
import keras
import pandas
import sklearn
import matplotlib

import pandas as pd

df = pd.read_csv('data.csv')

dataset = df.values

X = dataset[:,0:27]

Y = dataset[:, 8] ///I want column 8 to be my label column

from sklearn import preprocessing

min_max_scaler = preprocessing.MinMaxScaler()
X_scale = min_max_scaler.fit_transform(X)

from sklearn.model_selection import train_test_split
X_train, X_val_and_test, Y_train, Y_val_and_test = train_test_split(X_scale, Y, test_size=0.3)
X_val, X_test, Y_val, Y_test = train_test_split(X_val_and_test, Y_val_and_test, test_size=0.5)

from keras.models import Sequential
from keras.layers import Dense

model = Sequential([    
    Dense(32, activation='relu', input_shape=(27,)),    
    Dense(32, activation='relu'),    
    Dense(1, activation='softmax'),])

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


Ytest = keras.utils.to_categorical(Y_train,)
print('The one hot label is:', Y_train[5])

hist = model.fit(X_train, Ytest,
                 batch_size=32, epochs=20,          
                 validation_data=(X_val, Y_val))

错误:

ValueError: Error when checking target: expected dense_84 to have shape (1,) but got array with shape (11,)

我完全不知道这里出了什么问题。可以朝正确的方向轻推。

Answer 1

有两件事:

1 -看起来您忘记对 Y_train 进行一次热编码，错误表明您的最后一层需要形状为 [batch_size, 11] 的张量。

或

2 -最后一个密集层应该有 11 个节点而不是 1