本文介绍了pytorch conv2d值不能转换为uint8_t类型而不会溢出的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我正在传递 torch.Tensor ,其中 dtype torch.uint8 nn.Conv2d 模块,它给出了错误

I'm passing a torch.Tensor with a dtype of torch.uint8 to an nn.Conv2d module and it is giving the error

我的conv2d定义为 self.conv1 = nn.Conv2d(3,6,5)。当我将张量传递给 self.conv1(x)之类的模块时,错误出现在我的 forward 方法中。张量具有形状(4、3、480、640)。我不确定如何解决此问题。这是堆栈跟踪

My conv2d is defined as self.conv1 = nn.Conv2d(3, 6, 5). The error comes in my forward method when I pass the tensor to the module like self.conv1(x). The tensor has shape (4, 3, 480, 640). I'm not sure how to fix this. Here is the stack trace

Traceback (most recent call last):

  File "cnn.py", line 54, in <module>

    outputs = net(inputs)

  File "/Users/my_repos/venv_projc/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__

    result = self.forward(*input, **kwargs)

  File "cnn.py", line 24, in forward

    test = self.conv1(x)

  File "/Users/my_repos/venv_projc/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__

    result = self.forward(*input, **kwargs)

  File "/Users/my_repos/venv_projc/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 345, in forward

    return self.conv2d_forward(input, self.weight)

  File "/Users/my_repos/venv_projc/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 342, in conv2d_forward

    self.padding, self.dilation, self.groups)

RuntimeError: value cannot be converted to type uint8_t without overflow: -0.0344873


推荐答案

将张量转换为浮点数似乎可以解决它 self.conv1(x.float())

Converting the tensor to a float seemed to fix it self.conv1(x.float())

这篇关于pytorch conv2d值不能转换为uint8_t类型而不会溢出的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!

09-18 04:43