EnhanceNet-Tensorflow icon indicating copy to clipboard operation
EnhanceNet-Tensorflow copied to clipboard
verified publisher icon geonm

您好，想请问一下，关于识别过程中内存溢出的问题

Open Hannibal7ecter opened this issue 6 years ago • 3 comments

我有8G的显存，传入一张2000*2000的图片，内存溢出，请问有什么优化的方法吗？

Hannibal7ecter avatar Jul 15 '19 01:07 Hannibal7ecter

Hi Hinnibal7ecter!

simple approach:

  1. Slice your large image to several available size images like 720p or less
  2. Enhance sliced images separately
  3. Concatenate enhanced sliced images into one image

geonm avatar Jul 15 '19 04:07 geonm

谢谢你的回答，我正在尝试这种方法，不过我还是想弄明白，就是放大过程没有可优化的方法了吗？比如我的一张512*512的图片，我要放大8倍，我的8G显存的显卡，如果直接跑是肯定跑不过去的，是吗？

Hannibal7ecter avatar Jul 15 '19 04:07 Hannibal7ecter

Hannibal7ecter,

Please comment in English.

It's hard to understand your questions thr translator. :cry:

simple approach:

  • Run Enhancenet using CPU, not GPU.
  • Its free from 8GB GPU mem, but can be super slow to enhance images.

geonm avatar Jul 16 '19 07:07 geonm