【PyTorch_Bug】PT下问题记录

本文环境

• RuntimeError: bool value of Tensor with more than one value is ambiguous

错误：loss = torch.nn.MSELoss(predict,b_y) # 预测问题的损失
修正：

loss_func = torch.nn.MSELoss()
loss = loss_func(predict,b_y)

• RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 ‘self’ in call to _th_mm
  保存的是GPU模型，加载模型后输入的数据却是CPU数据
  修正：将数据加载进GPU方可。