python - pytorch conv2d 值不能在没有溢出的情况下转换为类型 uint8_t

Question

我正在传递一个 torch.Tensor与 dtype的 torch.uint8到 nn.Conv2d模块，它给出了错误

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

我的 conv2d 被定义为 self.conv1 = nn.Conv2d(3, 6, 5) .错误来自我的 forward当我将张量传递给模块时的方法，如 self.conv1(x) .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

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

Answer 1

将张量转换为浮点数似乎可以修复它 self.conv1(x.float())