代码拉取完成,页面将自动刷新
A version of matlab function 'imresize' using 'bicubic' interpolation, realized by pytorch and could acclearte by cuda. So it can be plug in nerual networks . While many interpolation methods in python like scipy.misc.imresize and torch.nn.function.Upsample(interpolation) and so on. They outputs different results with the results on matlab version. And I will update an python version 'bicubic' using numpy as soon as possible. And of course it can not acclerate by cuda, resulting slower results. images/monarch.png
#input image
#bicubic 1/4scale image
#bicubic 4scale image
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。