pytorch之Resize()函數

Resize函數用於對PIL圖像的預處理，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函數有兩個參數，

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 : 獲取輸出圖像的大小

interpolation : 插值，默認的  PIL.Image.BILINEAR， 一共有4中的插值方法

Image.BICUBIC，PIL.Image.LANCZOS，PIL.Image.BILINEAR，PIL.Image.NEAREST