search

dvlab-research / MASA-SR

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR2021)
161 stars 20 forks source link

输入chicun #25

Open Winnie202 opened 2 years ago

Winnie202 commented 2 years ago

请问一下训练集的尺寸只能是160×160吗？我在进行masa.pth训练的时候报错 AssertionError: Input spatial size must be 160x160, but received torch.Size([4, 3, 160, 288]).

SkyeLu commented 2 years ago

The input size only needs to be a multiple of 16.