本文介绍了pytorch conv2d 值无法在不溢出的情况下转换为类型 uint8_t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

我将带有 dtypetorch.uint8torch.Tensor 传递给 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

RuntimeError: 值不能被转换为类型 uint8_t溢出:-0.0344873

我的 conv2d 定义为 self.conv1 = nn.Conv2d(3, 6, 5).当我将张量传递给像 self.conv1(x) 这样的模块时,错误出现在我的 forward 方法中.张量的形状为 (4, 3, 480, 640).我不知道如何解决这个问题.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 值无法在不溢出的情况下转换为类型 uint8_t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!

07-12 01:58