报错处理整理

RuntimeError:_thnn_conv2d_forward not supported on CUPType for Byte

It seems you are trying to pass an input as a ByteTensor (uint8), which is not supported.
Could you call input = input.float() before passing it to the model

RuntimeError:Input type(torch.FloatTensor) and weight tpye (torch.cuda.FloatTensor) should be the same
错误内容大概就是指输入类型是CPU（torch.FloatTensor），而参数类型是GPU（torch.cuda.FloatTensor）

data = data.to(self.device)

pytorch 使用tenosorboard 可视化模型时
AttributeError: ‘torch._C.Value’ object has no attribute 'uniqueName’

https://github.com/lanpa/tensorboardX/issues/483
pytorch ,tensorboard python 等版本问题，1.2.0 切换到1.1.0，不报此错误