帝王谷资源网 Design By www.wdxyy.com

Resize函数用于对PIL图像的预处理,它的包在:

from torchvision.transforms import Compose, CenterCrop, ToTensor, Resize

使用如:

def input_transform(crop_size, upscale_factor):
  return Compose([
    CenterCrop(crop_size),
    Resize(crop_size // upscale_factor),
    ToTensor(),
  ])

而Resize函数有两个参数,

CLASS torchvision.transforms.Resize(size, interpolation=2)

size (sequence or int) – Desired output size. If size is a sequence like (h, w), output size will be matched to this. If size is an int, smaller edge of the image  will be matched to this number. i.e, if height > width, then image will be rescaled to (size * height / width, size)

interpolation (int, optional) – Desired interpolation. Default is PIL.Image.BILINEAR

size : 获取输出图像的大小

interpolation : 插值,默认的  PIL.Image.BILINEAR, 一共有4中的插值方法

Image.BICUBIC,PIL.Image.LANCZOS,PIL.Image.BILINEAR,PIL.Image.NEAREST
标签:
pytorch,Resize

帝王谷资源网 Design By www.wdxyy.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件! 如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
帝王谷资源网 Design By www.wdxyy.com