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

Question

一下为原代码，这种情况该如何解决啊

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

def predict_heart_disease(file_path):
    # 数据加载
    data = pd.read_csv(file_path, encoding='gbk')

    # 检查数据形状
    print(f'Data shape: {data.shape}')

    # 分离特征和目标变量
    if '是否患有心血管疾病' in data.columns:
        y = data['是否患有心血管疾病'].values
        X = data.drop('是否患有心血管疾病', axis=1).values

        # 数据预处理
        scaler = StandardScaler()
        X = scaler.fit_transform(X)

        # 检查特征数量
        print(f'Feature count: {X.shape[1]}')

        # 数据划分
        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

        # 构建模型
        model = Sequential()
        model.add(Dense(128, activation='relu', input_shape=(X_train.shape[1],)))
        model.add(Dense(64, activation='relu'))
        model.add(Dense(1, activation='sigmoid'))

        # 模型编译
        model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

        # 模型训练
        model.fit(X_train, y_train, epochs=10, batch_size=32)

        # 模型评估
        score = model.evaluate(X_test, y_test, verbose=0)
        print('Test loss:', score[0])
        print('Test accuracy:', score[1])

        # 新数据预测
        new_data = np.array([[65, 1, 3, 140, 260, 0, 2, 140, 1, 2.0, 3, 0, 6]]) # 这个数组需要根据你的实际特征来修改
        new_data = scaler.transform(new_data)
        prediction = model.predict(new_data)
        if prediction[0][0] >= 0.5:
            print('有心血管疾病')
        else:
            print('无心血管疾病')

# 文件列表
files = [r"C:\Users\1\Desktop\heart_disease\1-首次病程记录.csv", r"C:\Users\1\Desktop\heart_disease\2-日常病程记录.csv",
         r"C:\Users\1\Desktop\heart_disease\3-出院记录.csv", r"C:\Users\1\Desktop\heart_disease\4-检验记录表.csv",
         r"C:\Users\1\Desktop\heart_disease\5-检验明细表.csv", r"C:\Users\1\Desktop\heart_disease\6-细菌结果表.csv",
         r"C:\Users\1\Desktop\heart_disease\7-影像检查报告表.csv", r"C:\Users\1\Desktop\heart_disease\8-输出结果.csv"]

# 针对每一个文件运行函数
for file in files:
    print(f"Processing {file}")
    predict_heart_disease(file)

Answer 1

这就是类型转换错误，你得设定FLOAT

import torch
import numpy as np

arr1 = np.array([1,2,3], dtype=np.float32)
arr2 = np.array([4,5,6])
print(arr1.dtype)
print("nunpy中array的默认数据类型为：", arr2.dtype)

tensor = torch.tensor(arr2)
Tensor = torch.Tensor(arr2)
as_tensor = torch.as_tensor(arr2)
from_numpy = torch.from_numpy(arr2)

print(tensor.dtype, "|",Tensor.dtype, "|",as_tensor.dtype, "|",from_numpy.dtype)
arr2[0] = 10
print(tensor, Tensor, as_tensor, from_numpy)
'''
结果为：
float32
numpy中array的默认数据类型为： int64
torch.int64 | torch.float32 | torch.int64 | torch.int64
tensor([4, 5, 6]) tensor([4., 5., 6.]) tensor([10,  5,  6]) tensor([10,  5,  6])
'''