torch.FloatTensor()生成的数据类型dtype大小

结论

torch.FloatTensor()默认生成32位浮点数，dtype 为 torch.float32 或 torch.float

验证

     >>> tensor = torch.FloatTensor([[1,2],[3,4]])
     >>> print tensor
             tensor([[1., 2.],
             [3., 4.]])
     >>> print tensor.dtype    
             torch.float32

官网各类tensor对应数据类型如下：

https://pytorch.org/docs/stable/tensors.html?highlight=torch%20floattensor

Data type	dtype	CPU tensor	GPU tensor
32-bit floating point	torch.float32 or torch.float	torch.FloatTensor	torch.cuda.FloatTensor
64