神经网络-> ValueError：无法将NumPy数组转换为张量不支持的对象类型float

如何解决神经网络-> ValueError：无法将NumPy数组转换为张量不支持的对象类型float

我尝试建立具有回归的神经网络模型。我想e错误属于Feature Scaling，它试​​图从分类转换为数值（为性别列“ Male / Female”设置为OneHotEncoding）。

这是我的代码

import numpy as np 
import pandas as pd
import tensorflow as tf
import os
data1 = pd.read_csv(r"C:\Users\Cucu\Desktop\Mall_Customers.csv") 
x = data1.iloc [:,1:-1].values #SEParaTE INDEPENDENT VARIABLES
print(x)
y = data1.iloc [:,-1].values #SEParaTE DEPENDENT VARIABLES
print(y)
#AFTER PRINTING,WE WILL HAVE A SIMPLER SHEET


#ENCODING CATEGORICAL DATA
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer( transformers = [('encoder',OneHotEncoder(),[0] )],remainder = 'passthrough')
x = np.array(ct.fit_transform(x))
print (x)


#LET'S SPLIT INTO TRAIN SET & TEST 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 = 1 )
print(x_train)
print("------")
print(x_test)
print("------")
print(y_train)
print("------")
print(y_test)


#APPLYING FEATURE SCALING
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
x_train[:,2:] = sc.fit_transform(x_train[:,2:])
x_test[:,2:] = sc.transform(x_test[:,2:])
print(x_train)
#must be updated-------------------------


#INITIALZING THE ANN
ann = tf.keras.models.Sequential()

#BULDING THE ANN
ann.add(tf.keras.layers.Dense(units = 6,activation = 'relu'))
#--units(the number of neurons--hyper-parameter--must be optimized)



#ADDING THE INPUT LAYER &THE FirsT HIDDEN LAYER
ann.add(tf.keras.layers.Dense(units = 6,activation = 'relu'))

#ADDING THE OUPUT LAYER
ann.add(tf.keras.layers.Dense(units = 1,activation = 'relu'))  #ReLU used in output for regression task



#TRAINING THE ANN
#1)compiling the ann
ann.compile(optimizer = 'adam',loss = 'mean_squared_error' )
#mean_squared_error is specific loss fuction for regresion 


#2)training the ann on the training set
ann.fit(x_train,batch_size = 32,epochs = 100)

错误是：

File "D:\.spyder-py3\ANN.py",line 73,in <module>
    ann.fit(x_train,epochs = 100)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\keras\engine\training.py",line 819,in fit
    use_multiprocessing=use_multiprocessing)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py",line 235,line 593,in _process_training_inputs
    use_multiprocessing=use_multiprocessing)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py",line 706,in _process_inputs
    use_multiprocessing=use_multiprocessing)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\keras\engine\data_adapter.py",line 357,in __init__
    dataset = self.slice_inputs(indices_dataset,inputs)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\keras\engine\data_adapter.py",line 383,in slice_inputs
    dataset_ops.DatasetV2.from_tensors(inputs).repeat()

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\data\ops\dataset_ops.py",line 566,in from_tensors
    return TensorDataset(tensors)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\data\ops\dataset_ops.py",line 2765,in __init__
    element = structure.normalize_element(element)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\data\util\structure.py",line 113,in normalize_element
    ops.convert_to_tensor(t,name="component_%d" % i))

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\framework\ops.py",line 1314,in convert_to_tensor
    ret = conversion_func(value,dtype=dtype,name=name,as_ref=as_ref)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\framework\tensor_conversion_registry.py",line 52,in _default_conversion_function
    return constant_op.constant(value,dtype,name=name)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\framework\constant_op.py",line 258,in constant
    allow_broadcast=True)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\framework\constant_op.py",line 266,in _constant_impl
    t = convert_to_eager_tensor(value,ctx,dtype)

  File "C:\Users\Cucu\anaconda3\envs\lucky3\lib\site-packages\tensorflow_core\python\framework\constant_op.py",line 96,in convert_to_eager_tensor
    return ops.EagerTensor(value,ctx.device_name,dtype)

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float).

我尝试使用Google搜索，但没有找到任何解决方案。任何建议和帮助将不胜感激。