RuntimeError: “addmm_cuda“ not implemented for ‘Int‘

最新推荐文章于 2024-05-23 08:07:18 发布

Surupor

最新推荐文章于 2024-05-23 08:07:18 发布

阅读量6.7k

点赞数

分类专栏： pytorch Python编程人工智能原理文章标签：深度学习机器学习 python

本文链接：https://blog.csdn.net/sinat_38432876/article/details/126692360

版权

Python编程同时被 3 个专栏收录

5 篇文章 0 订阅

订阅专栏

pytorch

2 篇文章 0 订阅

订阅专栏

人工智能原理

2 篇文章 0 订阅

订阅专栏

cuda不支持整数的矩阵乘法

如下所示：

import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
a=torch.tensor([1,2,3],dtype=torch.int).to(device)
b=a.unsqueeze(dim=-1)@ a.unsqueeze(dim=0)
print(b)

结果

Traceback (most recent call last):
File "____mytest.py", line 5, in <module>
b=a.unsqueeze(dim=-1)@ a.unsqueeze(dim=0)
RuntimeError: "addmm_cuda" not implemented for 'Int'

但是当改成CPU时

import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
a=torch.tensor([1,2,3],dtype=torch.int)
b=a.unsqueeze(dim=-1)@ a.unsqueeze(dim=0)
print(b)

cuda
tensor([[1, 2, 3],
[2, 4, 6],
[3, 6, 9]], dtype=torch.int32)