Pytorch

• 英文文档：[1]
• 中文文档 [2][3]

网络初始化

• Xavier and Kaiming initialization [4]

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

• torch.eye(n, m=None, out=None)

返回一个2维张量，对角线位置全1，其它位置全0

• torch.view()

相当于numpy的reshape，某个维度上等于-1，就是让计算机自己算一下这一维度上应该有多少

Tensor

• cpu() numpy() detach() item() [5]

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 [6]
• __all__ = ["Compose", "ToTensor", "ToPILImage", "Normalize", "Resize",

"Scale", "CenterCrop", "Pad", "Lambda", "RandomCrop", "RandomHorizontalFlip", "RandomVerticalFlip", "RandomResizedCrop", "RandomSizedCrop", "FiveCrop", "TenCrop","LinearTransformation", "ColorJitter", "RandomRotation", "Grayscale", "RandomGrayscale"]