“Pytorch”的版本间差异

来自Shiyin's note
跳到导航 跳到搜索
无编辑摘要
第14行: 第14行:


==torchvision==
==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
*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",
[https://www.jianshu.com/p/1ae863c1e66d]
"Scale", "CenterCrop", "Pad", "Lambda", "RandomCrop",
"RandomHorizontalFlip", "RandomVerticalFlip", "RandomResizedCrop",
"RandomSizedCrop", "FiveCrop", "TenCrop","LinearTransformation",
"ColorJitter", "RandomRotation", "Grayscale", "RandomGrayscale"]

2021年10月17日 (日) 06:17的版本

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

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"]