Giters

LoSealL / VideoSuperResolution

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

FRVSR train problems

lius-xjtu opened this issue · comments

commented

Can you tell me which dataset your model is training on, and batchsize?

commented

I trained with vimeo data and found the color is wrong on the test image.

commented

I have trained with VIMEO too, is the wrong color shown on the validation board, or on inferred outputs?