查看“Pytorch”的源代码

*英文文档：[https://pytorch.org/docs/stable/index.html]
*中文文档  [https://pytorch.apachecn.org/][https://pytorch-cn.readthedocs.io/zh/latest/package_references/functional/#convolution]

==网络初始化==
*Xavier and Kaiming initialization [https://www.jianshu.com/p/f2d800388d1c]

==函数==
*torch.clamp(input, min=None, max=None, *, out=None) → Tensor
:Clamps all elements in input into the range [ min, max ]. Letting min_value and max_value be min and max, respectively

==Tensor==
* cpu() numpy() detach() item() [https://blog.csdn.net/ODIMAYA/article/details/102892799]
:注意cuda上面的变量类型只能是tensor，不能是其他