pytorch nn.Sigmoid函数好像只支持绝对值小于1数的计算

最新推荐文章于 2025-02-15 11:25:43 发布

佳hong

最新推荐文章于 2025-02-15 11:25:43 发布

阅读量2.6k

点赞数

分类专栏： python 学习文章标签： python PyTorch入门

本文链接：https://blog.csdn.net/zjh12312311/article/details/107306539

版权

学习同时被 2 个专栏收录

65 篇文章

订阅专栏

python

59 篇文章

订阅专栏

激活函数sigmoid

input = torch.randn(2,3)
print(input)

tensor([[-0.2863,  0.1606, -0.6738],
        [ 0.3379, -0.5613,  0.3672]])

X = torch.tensor([[1,2,3],[2,3,4]])
Y = mod(X)
print(Y)

---------------------------------------------------------------------------

RuntimeError                              Traceback (most recent call last)

<ipython-input-39-dac9d1ea9cc0> in <module>()
      1 X = torch.tensor([[1,2,3],[2,3,4]])
----> 2 Y = mod(X)
      3 print(Y)


E:\soft2\annaconda\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
    548             result = self._slow_forward(*input, **kwargs)
    549         else:
--> 550             result = self.forward(*input, **kwargs)
    551         for hook in self._forward_hooks.values():
    552             hook_result = hook(self, input, result)


E:\soft2\annaconda\lib\site-packages\torch\nn\modules\activation.py in forward(self, input)
    269 
    270     def forward(self, input):
--> 271         return torch.sigmoid(input)
    272 
    273 


RuntimeError: "sigmoid_cpu" not implemented for 'Long'

X = torch.tensor([[0.1,0.2,0.3],[0.2,0.3,0.4]])
print(X)
mod = nn.Sigmoid()
Y = mod(X)
y = mod(input)
print(Y)
print(y)

tensor([[0.1000, 0.2000, 0.3000],
        [0.2000, 0.3000, 0.4000]])
tensor([[0.5250, 0.5498, 0.5744],
        [0.5498, 0.5744, 0.5987]])
tensor([[0.4289, 0.5401, 0.3377],
        [0.5837, 0.3633, 0.5908]])