How would one go about training the network with one channel images?

soumith / ganhacks

starter from "How to Train a GAN?" at NIPS2016

11.43k stars 1.66k forks source link

How would one go about training the network with one channel images? #34

Open patakk opened 6 years ago

patakk commented 6 years ago

Let's say I have normal RGB images and would like to only take the Y component of the YUV color space, how would one go about doing that and setting up tfrecords?

makeyourownalgorithmicart commented 5 years ago

I don't know TF but I suspect it is similar to pytorch

you simply provide images with dimensions (xsize, ysize, depth) where depth is not 3 (RGB) but 1 (Y)

patakk commented 5 years ago

I honestly can't remember why I even asked this question, but I guess I wanted to know how to convert RGB images to grayscale and save it to tfrecords, but I could've just googled it..