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

==torchvision==
*PyTorch框架中有一个非常重要且好用的包：torchvision，该包主要由3个子包组成，分别是：torchvision.datasets、torchvision.models、torchvision.transforms [https://www.jianshu.com/p/1ae863c1e66d]
*__all__ = ["Compose", "ToTensor", "ToPILImage", "Normalize", "Resize",
"Scale", "CenterCrop", "Pad", "Lambda", "RandomCrop", 
"RandomHorizontalFlip", "RandomVerticalFlip", "RandomResizedCrop", 
"RandomSizedCrop", "FiveCrop", "TenCrop","LinearTransformation", 
"ColorJitter", "RandomRotation", "Grayscale", "RandomGrayscale"]