pytorch奇怪错误

我的心永远是冰冰哒2024-11-19 23:58

复制代码

ValueError: At least one stride in the given numpy array is negative, and tensors with negative strides are not currently supported. (You can probably work around this by making a copy of your array  with array.copy().)

今天在这里遇到了一个奇怪的bug

复制代码

import numpy as np

# 创建一个简单的数组
array = np.array([1, 2, 3, 4, 5])

# 使用反向切片创建负步幅数组
reversed_array = array[::-1]

print("原始数组:", array)
print("反向切片后的数组:", reversed_array)
print("反向数组的步幅:", reversed_array.strides)

结果如下

复制代码

import torch 
aa = torch.FloatTensor(array)
bb = torch.FloatTensor(reversed_array)

正确用法

复制代码

import torch 
aa = torch.FloatTensor(array)
bb = torch.FloatTensor(reversed_array.copy())

这个结果是